SlideShare ist ein Scribd-Unternehmen logo
1 von 122
Downloaden Sie, um offline zu lesen
Learning Multilingual Semantic Parsers for 

Question Answering over Linked Data
A comparison of neural and probabilistic graphical model architectures
PhD Dissertation Defense Talk

March 2019
Sherzod Hakimov
Semantic Computing Group, CITEC

Bielefeld University
Outline
1. Introduction

2. Motivation & Problem

3. Preliminaries

4. Dependency parse tree-based Semantic Parsing Approach

5. Evaluation of different architectural choices for “simple question” answering

6. Discussion

7. Conclusion
2
Introduction
3
Introduction
44
Human-machine interaction
Give me the route to Jahnplatz
Introduction
55
Human-machine interaction
Give me the route to Jahnplatz
?
Introduction
66
Human-machine interaction
? Knowledge Base
6
7
Give me the route to Jahnplatz
What is Semantic Parsing?
• mapping natural language sentence to a detailed meaning representation
8
Give me the route to Jahnplatz
route($LOC, “Jahnplatz”)
What is Semantic Parsing?
• mapping natural language sentence to a detailed representation of meaning representation
route(StartLocation, EndLocation)
9
Give me the route to Jahnplatz
route($LOC, “Jahnplatz”)
What is Semantic Parsing?
• mapping natural language sentence to a detailed representation of meaning representation

• meaning representation can be modelled using a formal language that
10
Give me the route to Jahnplatz
route($LOC, “Jahnplatz”)
What is Semantic Parsing?
• mapping natural language sentence to a detailed representation of meaning representation

• meaning representation can be modelled using a formal language, e.g. lambda calculus

• an ontology with properties, classes, entities, etc. (route, create_calendar_event, set_alarm)

• supports automated execution or reasoning
11
Give me the route to Jahnplatz Query
Knowledge Base
Answer
Why do we need Semantic Parsers?
route($LOC, “Jahnplatz”)
12
Give me the route to Jahnplatz Query
Knowledge Base
Answer
Why do we need Semantic Parsers?
route($LOC, “Jahnplatz”)
Motivation
• Building semantic parsers with application on Question Answering
13
Linked Data Cloud
Motivation
• Building semantic parsers with application on Question Answering

• Building multilingual solutions that can be applied for multiple languages
14
Which German politicians were born in Bielefeld?
Which metal has a liquid form?
Welche deutschen Politiker wurden in Bielefeld geboren?
Welches Metall hat eine flüssige Form?
¿Qué políticos alemanes nacieron en Bielefeld?
¿Qué metal tiene una forma líquida?
Motivation
• Building semantic parsers with application on Question Answering

• Building multilingual solutions that can be extended for other languages

• Comparison and evaluation of different model architectures
15
Motivation
• Building semantic parsers with application on Question Answering

• Building multilingual solutions that can be extended for other languages

• Comparison and evaluation of different model architectures 

• Highlight the challenges of building Question Answering systems
16
• based on structured content from Wikipedia

• more than 130 languages supported 

• 760 classes, 1105 object & 1622 data type properties

• ca. 9 million resources
17
dbr:Dan_Brown
dbo:author
dbo:author
dbr:Tom_Hanks
dbo:starring
dbo:starring
dbo:basedOn
dbo:basedOn
dbo:Writer dbo:Book dbo:Film dbo:Actor
DBpedia Ontology & Data
18
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)
19
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)Triple: dbr:Inferno_(novel) dbo:author dbr:Dan_Brown
20
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)
Dan Brown is the author of Inferno
Triple:
Natural Language:
dbr:Inferno_(novel) dbo:author dbr:Dan_Brown
21
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)
Dan Brown is the author of Inferno
Who is the author of Inferno?Natural Language:
Question format
dbr:Inferno_(novel) dbo:author dbr:Dan_BrownTriple:
Natural Language:
22
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)
Dan Brown is the author of Inferno
dbr:Inferno_(novel) dbo:author dbr:Dan_BrownTriple:
Natural Language:
Who is the author of Inferno?Natural Language:
SPARQL Query:
Question format
SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x}
23
dbr:Dan_Brown
dbo:author
Question Answering on RDF Data
dbr:Inferno_(novel)Who is the author of Inferno?
Semantic Parser
SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x}
24
Research Questions
How to map natural language phrases into knowledge base entries for multiple languages?
Which linguistic resources can be used?
25
dbr:Dan_Brown
dbo:author
Who is the author of Inferno? dbr:Inferno_(novel)
Who wrote Inferno?
Who is the writer of Inferno?
SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x}
Research Questions
How to map natural language phrases into knowledge base entries for multiple languages?
Which linguistic resources can be used?
26
dbr:Dan_Brown
dbo:author
Who is the author of Inferno? dbr:Inferno_(novel)
Who wrote Inferno?
Who is the writer of Inferno?
SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x}
Lexical Gap: write -> dbo:author
Research Questions
How to disambiguate URIs when multiple candidates are retrieved from mapping natural
language tokens into knowledge base entries?
27
When was Inferno released?
SELECT ?x WHERE {dbr:Inferno_(novel) dbo:releaseDate ?x}
dbr:Inferno_(2016_film) dbr:Inferno_(novel)
Research Questions
How to use syntactic information of a natural language question together with semantic
representations of entries in a knowledge base?
28
Who wrote Inferno?
dbr:Dan_Brown
dbo:author
dbr:Inferno_(novel)
SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x }
wrote

(VERB)
Who

(PRON)
Inferno

(PROPN)
nsubj dobj
Research Questions
What are the advantages and the disadvantages of a multilingual QA system vs. a
monolingual system built for each language?
29
Who is the author of Inferno? dbr:Dan_Brown
dbo:author
dbr:Inferno_(novel)
Wer ist der Autor von Inferno?
¿Quién es el autor de Inferno?
SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x }
Research Questions
What effort is required to adapt our QA pipelines to another language?
30
Who is the author of Inferno? dbr:Dan_Brown
dbo:author
dbr:Inferno_(novel)
Qui est l'auteur de Inferno?
Infernoning muallifi kim?
SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x }
Preliminaries
31
Preliminaries
• Logical Form - DUDES, formalism for specifying meaning representations for dependency tree
structures

32
Preliminaries
• Logical Form - DUDES, formalism for specifying meaning representations for dependency tree
structures

• Semantic Composition - acquiring the meaning representations using the syntax of questions
33
Logical Form
34
•	 DUDES - Dependency-based Underspecified Discourse Representation Structures (Cimiano et al [1])

[1] Cimiano, P., 2009, Flexible semantic composition with DUDES. In Proceedings of the Eighth International Conference on
Computational Semantics (pp. 272-276). Association for Computational Linguistics.
Logical Form
35
•	 DUDES - Dependency-based Underspecified Discourse Representation Structures (Cimiano et al [1])

•	 Formalism for specifying meaning representation

•	 Flexible semantic composition w.r.t order of application

•	 Build on semantic dependencies e.g. suitable for working with dependency-based syntactic analysis

[1] Cimiano, P., 2009, Flexible semantic composition with DUDES. In Proceedings of the Eighth International Conference on
Computational Semantics (pp. 272-276). Association for Computational Linguistics.
DUDES
v : is the main variable
vs : the projection variables
l : is the label of the main DRS
drs : is a DRS (Discourse Representation Structure)
slots : is a set of semantic dependencies
36
Semantic Composition with DUDES
Who created Wikipedia?
Input: a natural language question and its dependency parse tree
37
Semantic Composition with DUDES
Who created Wikipedia?
Input: a natural language question and its dependency parse tree
dbr:Wikipedia dbo:author ?x
Output: a meaning representation based on certain domain
38
Semantic Composition with DUDES
Each node gets a pair of assignments: DUDES Type + Knowledge base ID
Oracle
39
Semantic Composition with DUDES - Bottom Up
40
Semantic Composition with DUDES - Bottom Up
41
1
2
Semantic Composition with DUDES - Bottom Up
42
2
Semantic Composition with DUDES - Bottom Up
43
2
Semantic Composition with DUDES - Bottom Up
44
2
Semantic Composition with DUDES - Bottom Up
45
x
Semantic Composition with DUDES
46
Logical Form into SPARQL
47
Dependency parse tree-based
Semantic Parsing Approach
48
Dependency parse tree-based Semantic Parsing
Approach
• multilingual semantic parsing approach: English, German & Spanish [1]
49
[1] Hakimov S, Jebbara S, Cimiano P. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data.
In Proceedings of the 16th International Semantic Web Conference (ISWC), 2017
Dependency parse tree-based Semantic Parsing
Approach
• multilingual semantic parsing approach: English, German & Spanish [1]

• uses language-independent dependency parse trees from Universal
Dependencies
50
[1] Hakimov S, Jebbara S, Cimiano P. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data.
In Proceedings of the 16th International Semantic Web Conference (ISWC), 2017
Dependency parse tree-based Semantic Parsing
Approach
• multilingual semantic parsing approach: English, German & Spanish [1]

• uses language-independent dependency parse trees from Universal
Dependencies

• combines different types of lexical information: DBpedia Ontology labels,
the M-ATOLL[2] lexicon & word embeddings
51
[1] Hakimov S, Jebbara S, Cimiano P. “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked
Data”. ISWC 2017
[2] Walter S, Unger C, and Cimiano P. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple
Languages”. ISWC 2014
[3] Hakimov S, Walter S, Unger C, and Cimiano P. “Applying semantic parsing to question answering over linked data:
Addressing the lexical gap”. NLDB 2015
Dependency parse tree-based Semantic Parsing Approach
Oracle
SELECT ?x WHERE { dbr:Wikipedia dbo:author ?x. }
Semantic Composition
52
Dependency parse tree-based Semantic Parsing Approach
Oracle
SELECT ?x WHERE { dbr:Wikipedia dbo:author ?x. }
Semantic Composition
Structure Learning
53
Dependency parse tree-based Semantic Parsing
Approach
• inference

• factor graph model
54
Inference
• Metropolis-Hastings: exploring huge search space (ca. 10 million resources, 2000 properties)
• Linking to Knowledge Base (L2KB)
•objective : compare set of URIs to the expected set of URIs
• Query Construction (QC)
•objective : compare the constructed query to the expected query
55
Input: initial state
L2KB Sampling
Explore the edges and assign Knowledge Base IDs based on lemmas of nodes
Inverted index: Ontology labels, lexicon from M-ATOLL & word embeddings
56
L2KB Sampling
Explore the edges and assign Knowledge Base IDs based on lemmas of nodes
Check the triple pattern- ?x dbo:author dbr:Wikipedia : Slot 2, dbr:Wikipedia dbo:author ?x : Slot1
Inverted index: Ontology labels, lexicon from M-ATOLL & word embeddings
57
58
59
60
QC Sampling
Assign DUDES with Return Variable and KB ID to nodes and assign remaining slots
61
Inference
62
m steps
Model Representation
63
Observed variables: dependency parse tree
Hidden variables: KB IDs, slot, DUDE types
Model Representation
64
Observed variables: dependency parse tree
Hidden variables: KB IDs, slot, DUDE types
Model Representation
65
Observed variables: dependency parse tree
Hidden variables: KB IDs, slot, DUDE types
Child_Node [POS: PROPN, DUDES: Resource] Parent_Node [POS: VERB, DUDES:Property]
Sample Feature
Evaluation
Dataset: Question Answering over Linked Data (QALD), 6th challenge
English, German, Spanish, Italian, French, Dutch, Romanian, Farsi
350 for train, 100 for test
Unger, Christina, Axel-Cyrille Ngonga Ngomo, and Elena Cabrio (2016). “6th open challenge on question
answering over linked data (qald-6)”. In: Semantic Web Evaluation Challenge.
66
Evaluation
DBP: lexicon from DBpedia Ontology & WordNet

M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)

Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013)
Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014
Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013
67
Evaluation
DBP: lexicon from DBpedia Ontology & WordNet

M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)

Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013)

Dict: manually defined lexicon
Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014
Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013
68
Evaluation
DBP: lexicon from DBpedia Ontology & WordNet

M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)

Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013)

Dict: manually defined lexicon
Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014
Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013
69
Evaluation of Lexicon
70
English German Spanish
Evaluation of different architectural
choices for “simple question”
answering
71
Outline
• SimpleQuestions dataset, 74k samples, Freebase data

• Question: “Who wrote Mildred Pierced?” 

• Fact: mildred_pierced, book.written_work.author, stuart_kaminsky

• Answer: mildred_pierced, book.written_work.author, ?x

• Systematic comparison of different model architectures
72
Hakimov S, Jebbara S, Cimiano P. “Evaluating Architectural Choices for Deep Learning Approaches for Question
Answering over Knowledge Bases”. ICSC 2019
Named Entity Recognition
• Used by all models to predict the entity span

• Character & word embeddings

• Trained using weak supervision: inference is correct if the
expected entity has been found
73
Candidate Retrieval
Candidate pairs: subject and predicate
74
Surface form frequencies
Model1: BiLSTM-Softmax
75
Model2: BiLSTM-KB Model3: BiLSTM-Binary Model4: Fasttext [1]
Architectures
[1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, "Bag of Tricks for Efficient Text Classification", 2016, arxiv.org
Model1: BiLSTM-Softmax
76
Model2: BiLSTM-KB Model3: BiLSTM-Binary Model4: Fasttext [1]
Architectures
[1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, "Bag of Tricks for Efficient Text Classification", 2016, arxiv.org
Evaluation
77
Named Entity Linking
Named Entity Recognition
Predicate & Answer Prediction
Evaluation
78
Named Entity Linking
Named Entity Recognition 0,82
Predicate & Answer Prediction
Evaluation
79
Named Entity Linking
Named Entity Recognition 0,82
Predicate & Answer Prediction
Evaluation
80
Named Entity Linking
Named Entity Recognition 0,82
Predicate & Answer Prediction
Discussion
81
Discussion
• Manual Effort

• Syntax and Semantics

• Multilinguality

• Cross-domain Transferability

• Training Data Size and Search Space
82
Discussion
83
Systems Manual Effort Syntax & Semantics Multilinguality
Cross-domain
transferability
Training Data & 

Number of KB IDs
CCG-based

(Chapter 6)
CCG combination rules

manual lexicon
• learned in tandem

• CCG for syntax

• lambda calculus for semantics
manual effort is required manual effort is required
600 training instances

750 entities
Dependency-
based

(Chapter 7)
feature templates
syntax is given

DUDES as a formalism
an adaptable solution
• a dependency parser
required.

• e.g. biomedical domain
300 training instances

<= 10 mil. entities

>= 2000 predicates
BiLSTM-Softmax

(Chapter 8)
-
• word & char embed. for lexical
& contextual info

• semantics is limited to a single
predicate and a subject entity
an adaptable solution

only word & char
embed.
an adaptable solution

only word & char embed.
>= 75K instances

<= 2 mil. entities
Research Questions
84
Research Questions
85
• Ontology lexicalisations, e.g. M-ATOLL (Walter et al. 2014)

• Ontology labels, e.g. DBpedia labels

• Dictionaries

• WordNet synsets

• Induced from contextual embeddings of words
RQ1: How to map natural language phrases into knowledge base entries for
multiple languages? Which linguistic resources can be used?
Research Questions
86
• Supervised models with objective for disambiguation

• CCG-based model

• uses lexical and syntactic information as features

• Dependency tree-based model

• syntactic dependency between words, lexical similarity, ontology restrictions

• Neural network-based model

• ranking objective of predicates
RQ2: How to disambiguate URIs when multiple candidates are retrieved from
mapping natural language tokens into knowledge base entries?
Research Questions
87
• Semantic Parsing

• bottom-up composition

• CCG-based model

• learns the syntax and semantics together

• Dependency tree-based model

• learns composing semantics based on dependency trees

RQ3: How to use syntactic information of a natural language question together
with semantic representations of entries in a knowledge base?
Research Questions
88
RQ4: What are the advantages and the disadvantages of a multilingual QA system
vs. a monolingual system built for each language?
• Advantages

• Multilingual: broader coverage

• Monolingual: higher performance, e.g. Xser (Xu et al. 2014) 0.7 F1 on QALD-4

• Disadvantages

• Multilingual: lower performance, e.g. AMUSE 0.3 F1 on QALD-6

• Monolingual: need expertise, e.g. CCG rules, lexicon
Research Questions
89
• CCG-based model

• grammar rules, manually defined lexicon

• language-specific

• Dependency parse tree-based model

• dependency parse tree generator

• lexicon

• Neural network-based model

• depends on the training data

RQ5: What effort is required to adapt our QA pipelines to another language?
Conclusion
• Address the lexical gap for QA systems

• Incorporate ontology lexicalizations to reduce the lexical gap

• Use Universal Dependencies to build language-independent QA pipeline

• Multilingual semantic parsing for Question Answering

• Evaluate different QA models under the certain conditions

• Highlight importance of building blocks of a pipeline for a fair comparison
90
CCG-based Semantic Parsing Approach
91
GENLEX
Barack Obama is married to Michelle Obama
[1] Zettlemoyer, Luke S and Michael Collins (2005). “Learning to Map Sentences to Logical Form : Structured
Classification with Probabilistic Categorial Grammars”. In: 21st Conference on Uncertainty in Artificial Intelligence
[2] Hakimov, Sherzod et al. (2015). “Applying semantic parsing to question answering over linked data: Addressing the lexical
gap”. In: International Conference on Applications of Natural Language to Information Systems 92
CCG & GENLEX Rules
93
Semantic Composition
Barack Obama is married to Michelle Obama
94
Evaluation QALD-4
95
Lexicon
During sampling, compute cosine similarity of words into Ontology labels of properties

Vectors for multiple words are summed, e.g. V(population) + V(total)
96
Lexicon
Restriction Class
97
Dataset - GeoQuery
600 train, 280 test instances
98
Dataset - QALD
99
Dataset-QALD
100
Dataset - SimpleQuestions
Train: 75,910
Validation: 10,845
Test: 21,687
Total: 108,442
101
Dataset Complexity
Lexical Overlap, tokens exist in both
102
Semantic Composition
•recursively computing the meaning of each node from the meanings of its child nodes
•build the meaning representation bottom-up
ComposeSemantics(dependency-parse-tree)
If parse-tree is a terminal node (word) then
return an atomic lexical meaning for the word.
Else
For each child, subtreei, of parse-tree
Create its MR by calling ComposeSemantics(subtreei)
Return an MR by properly combining the resulting MRs
for its children into an MR for the overall parse-tree.
103
Features
104
Feature Templates
105
L2KB QC
L2KB Features
106
QC Features
107
Model Representation
108
Observed variables: dependency parse tree
Hidden variables: KB IDs, slot, DUDE types
• States can be ranked by

• objective score : compare to ground truth

• model score: computed using feature weights

• Training procedures

• switch between model & objective score after every iteration
Chapter 8
109
Model Score
110
Model1: BiLSTM-Softmax
• Softmax layer that predicts predicates seen
during training

• Encoding layer: word & character

• BiLSTM: two LSTM layers (backward, forward)
111
Model2: BiLSTM-KB
• Learn embedding of predicates in KB

• Encoding layer: word & character

• BiLSTM: two LSTM layers (backward, forward)

• Output layer computes cosine similarity to all
predicates and chooses the closest
112
Model3: BiLSTM-Binary
• Encoding layer: encodes input question with word &
character embeddings

• Encoding layer: encodes input predicate with word &
character embeddings

• Output layer: binary decision
113
Model4: Fasttext
• Document classification tool developed by Facebook*

• Uses word & character embeddings

• Softmax layer that predicts the expected predicate
114
* http://fasttext.cc
Factor Graph
115
116
Generative Models -> computing joint probability distribution on p(y|x)

HMM -> y_t depends on y_t-1 and x_t
how output label y_t generates input vector x
Discriminative Models -> computing conditional probability distribution over inputs x and outputs y

CRF -> doesn’t have any limitation like that
how feature vector x gets assignment y_t
Discussion
117
Manual Effort
• CCG-based model

• define CCG grammar rules, hand-crafted lexicon for domain independent phrases

• Dependency parse tree-based model 

• feature functions

• Neural network-based model (BiLSTM-Softmax)

• not required
118
Syntax and Semantics
• CCG-based model

• syntax and semantics is learned in tandem

• CCG for syntax and the lambda calculus for semantics

• syntax guides the semantics of the sentences

• Dependency parse tree-based model 

• syntax is given and the semantics is learned

• DUDES as a formalism for semantics, syntax is based on dependency trees from Universal Dependencies

• Neural network-based model (BiLSTM-Softmax)

• syntactic information is learned, e.g. word and character embeddings provide contextual information

• semantics is based on a single subject and the predicate, simpler task
119
Multilinguality
• CCG-based model

• CCG grammar rules needs to be extended

• Dependency parse tree-based model 

• a multilingual solution

• Neural network-based model (BiLSTM-Softmax)

• can be adapted to other languages, e.g. word & characters as features
120
Cross-domain Transferability
• CCG-based model

• manual effort is required: CCG rules, lexicon

• Dependency parse tree-based model 

• dependency parse trees e.g. biomedical domain

• Neural network-based model (BiLSTM-Softmax)

• can be easily adapted
121
Training Data Size and Search Space
• CCG-based model

• Dependency parse tree-based model

• Neural network-based model (BiLSTM-Softmax) 

• heavily depends on the data
122

Weitere ähnliche Inhalte

Was ist angesagt?

Natural Language Processing in R (rNLP)
Natural Language Processing in R (rNLP)Natural Language Processing in R (rNLP)
Natural Language Processing in R (rNLP)fridolin.wild
 
Named entity recognition (ner) with nltk
Named entity recognition (ner) with nltkNamed entity recognition (ner) with nltk
Named entity recognition (ner) with nltkJanu Jahnavi
 
Ir 1 lec 7
Ir 1 lec 7Ir 1 lec 7
Ir 1 lec 7alaa223
 
Text Mining Infrastructure in R
Text Mining Infrastructure in RText Mining Infrastructure in R
Text Mining Infrastructure in RAshraf Uddin
 
Chapter 10 Data Mining Techniques
 Chapter 10 Data Mining Techniques Chapter 10 Data Mining Techniques
Chapter 10 Data Mining TechniquesHouw Liong The
 
Copy of 10text (2)
Copy of 10text (2)Copy of 10text (2)
Copy of 10text (2)Uma Se
 
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...JohannWanja
 
RDF2Vec: RDF Graph Embeddings for Data Mining
RDF2Vec: RDF Graph Embeddings for Data MiningRDF2Vec: RDF Graph Embeddings for Data Mining
RDF2Vec: RDF Graph Embeddings for Data MiningPetar Ristoski
 
DS2014: Feature selection in hierarchical feature spaces
DS2014: Feature selection in hierarchical feature spacesDS2014: Feature selection in hierarchical feature spaces
DS2014: Feature selection in hierarchical feature spacesPetar Ristoski
 
Information Extraction from the Web - Algorithms and Tools
Information Extraction from the Web - Algorithms and ToolsInformation Extraction from the Web - Algorithms and Tools
Information Extraction from the Web - Algorithms and ToolsBenjamin Habegger
 
Lecture: Question Answering
Lecture: Question AnsweringLecture: Question Answering
Lecture: Question AnsweringMarina Santini
 
Performance of graph query languages
Performance of graph query languagesPerformance of graph query languages
Performance of graph query languagesAthiq Ahamed
 
Enriching the semantic web tutorial session 1
Enriching the semantic web tutorial session 1Enriching the semantic web tutorial session 1
Enriching the semantic web tutorial session 1Tobias Wunner
 

Was ist angesagt? (20)

Natural Language Processing in R (rNLP)
Natural Language Processing in R (rNLP)Natural Language Processing in R (rNLP)
Natural Language Processing in R (rNLP)
 
Named entity recognition (ner) with nltk
Named entity recognition (ner) with nltkNamed entity recognition (ner) with nltk
Named entity recognition (ner) with nltk
 
Ir 1 lec 7
Ir 1 lec 7Ir 1 lec 7
Ir 1 lec 7
 
Text Mining Infrastructure in R
Text Mining Infrastructure in RText Mining Infrastructure in R
Text Mining Infrastructure in R
 
Chapter 10 Data Mining Techniques
 Chapter 10 Data Mining Techniques Chapter 10 Data Mining Techniques
Chapter 10 Data Mining Techniques
 
Copy of 10text (2)
Copy of 10text (2)Copy of 10text (2)
Copy of 10text (2)
 
Web and text
Web and textWeb and text
Web and text
 
Text Indexing / Inverted Indices
Text Indexing / Inverted IndicesText Indexing / Inverted Indices
Text Indexing / Inverted Indices
 
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...
TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from th...
 
RDF2Vec: RDF Graph Embeddings for Data Mining
RDF2Vec: RDF Graph Embeddings for Data MiningRDF2Vec: RDF Graph Embeddings for Data Mining
RDF2Vec: RDF Graph Embeddings for Data Mining
 
DS2014: Feature selection in hierarchical feature spaces
DS2014: Feature selection in hierarchical feature spacesDS2014: Feature selection in hierarchical feature spaces
DS2014: Feature selection in hierarchical feature spaces
 
SWT Lecture Session 8 - Rules
SWT Lecture Session 8 - RulesSWT Lecture Session 8 - Rules
SWT Lecture Session 8 - Rules
 
SWT Lecture Session 3 - SPARQL
SWT Lecture Session 3 - SPARQLSWT Lecture Session 3 - SPARQL
SWT Lecture Session 3 - SPARQL
 
Information Extraction from the Web - Algorithms and Tools
Information Extraction from the Web - Algorithms and ToolsInformation Extraction from the Web - Algorithms and Tools
Information Extraction from the Web - Algorithms and Tools
 
Link Discovery Tutorial Part I: Efficiency
Link Discovery Tutorial Part I: EfficiencyLink Discovery Tutorial Part I: Efficiency
Link Discovery Tutorial Part I: Efficiency
 
Link Discovery Tutorial Part V: Hands-On
Link Discovery Tutorial Part V: Hands-OnLink Discovery Tutorial Part V: Hands-On
Link Discovery Tutorial Part V: Hands-On
 
Lecture: Question Answering
Lecture: Question AnsweringLecture: Question Answering
Lecture: Question Answering
 
Link Discovery Tutorial Part II: Accuracy
Link Discovery Tutorial Part II: AccuracyLink Discovery Tutorial Part II: Accuracy
Link Discovery Tutorial Part II: Accuracy
 
Performance of graph query languages
Performance of graph query languagesPerformance of graph query languages
Performance of graph query languages
 
Enriching the semantic web tutorial session 1
Enriching the semantic web tutorial session 1Enriching the semantic web tutorial session 1
Enriching the semantic web tutorial session 1
 

Ähnlich wie Learning Multilingual Semantic Parsers for Question Answering over Linked Data - A comparison of neural and probabilistic graphical model architectures

Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information RetrievalRoelof Pieters
 
The web of interlinked data and knowledge stripped
The web of interlinked data and knowledge strippedThe web of interlinked data and knowledge stripped
The web of interlinked data and knowledge strippedSören Auer
 
From Semantics to Self-supervised Learning for Speech and Beyond (Opening Ke...
From Semantics to Self-supervised Learning  for Speech and Beyond (Opening Ke...From Semantics to Self-supervised Learning  for Speech and Beyond (Opening Ke...
From Semantics to Self-supervised Learning for Speech and Beyond (Opening Ke...linshanleearchive
 
Getting Started with Knowledge Graphs
Getting Started with Knowledge GraphsGetting Started with Knowledge Graphs
Getting Started with Knowledge GraphsPeter Haase
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Andre Freitas
 
DODDLE-OWL: A Domain Ontology Construction Tool with OWL
DODDLE-OWL: A Domain Ontology Construction Tool with OWLDODDLE-OWL: A Domain Ontology Construction Tool with OWL
DODDLE-OWL: A Domain Ontology Construction Tool with OWLTakeshi Morita
 
Multilingual qa
Multilingual qaMultilingual qa
Multilingual qashakimov
 
Identifying Topics in Social Media Posts using DBpedia
Identifying Topics in Social Media Posts using DBpediaIdentifying Topics in Social Media Posts using DBpedia
Identifying Topics in Social Media Posts using DBpediaÓscar Muñoz García
 
Understanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesUnderstanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesAshis Kumar Chanda
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Bhaskar Mitra
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsRoelof Pieters
 
Scalable Cross-lingual Document Similarity through Language-specific Concept ...
Scalable Cross-lingual Document Similarity through Language-specific Concept ...Scalable Cross-lingual Document Similarity through Language-specific Concept ...
Scalable Cross-lingual Document Similarity through Language-specific Concept ...Carlos Badenes-Olmedo
 
Understanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesUnderstanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesAshis Chanda
 
A Panorama of Natural Language Processing
A Panorama of Natural Language ProcessingA Panorama of Natural Language Processing
A Panorama of Natural Language ProcessingTed Xiao
 
Approach to leverage Websites to APIs through Semantics
Approach to leverage Websites to APIs through SemanticsApproach to leverage Websites to APIs through Semantics
Approach to leverage Websites to APIs through SemanticsIoannis Stavrakantonakis
 
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)rchbeir
 
What you Can Make Out of Linked Data
What you Can Make Out of Linked DataWhat you Can Make Out of Linked Data
What you Can Make Out of Linked DataMarco Fossati
 
Session 0.0 aussenac semanticsnl-pwebsem2017-v4
Session 0.0   aussenac semanticsnl-pwebsem2017-v4Session 0.0   aussenac semanticsnl-pwebsem2017-v4
Session 0.0 aussenac semanticsnl-pwebsem2017-v4semanticsconference
 

Ähnlich wie Learning Multilingual Semantic Parsers for Question Answering over Linked Data - A comparison of neural and probabilistic graphical model architectures (20)

Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information Retrieval
 
The web of interlinked data and knowledge stripped
The web of interlinked data and knowledge strippedThe web of interlinked data and knowledge stripped
The web of interlinked data and knowledge stripped
 
From Semantics to Self-supervised Learning for Speech and Beyond (Opening Ke...
From Semantics to Self-supervised Learning  for Speech and Beyond (Opening Ke...From Semantics to Self-supervised Learning  for Speech and Beyond (Opening Ke...
From Semantics to Self-supervised Learning for Speech and Beyond (Opening Ke...
 
semantic web & natural language
semantic web & natural languagesemantic web & natural language
semantic web & natural language
 
Getting Started with Knowledge Graphs
Getting Started with Knowledge GraphsGetting Started with Knowledge Graphs
Getting Started with Knowledge Graphs
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...
 
DODDLE-OWL: A Domain Ontology Construction Tool with OWL
DODDLE-OWL: A Domain Ontology Construction Tool with OWLDODDLE-OWL: A Domain Ontology Construction Tool with OWL
DODDLE-OWL: A Domain Ontology Construction Tool with OWL
 
Multilingual qa
Multilingual qaMultilingual qa
Multilingual qa
 
Identifying Topics in Social Media Posts using DBpedia
Identifying Topics in Social Media Posts using DBpediaIdentifying Topics in Social Media Posts using DBpedia
Identifying Topics in Social Media Posts using DBpedia
 
Understanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesUnderstanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational Databases
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
 
Scalable Cross-lingual Document Similarity through Language-specific Concept ...
Scalable Cross-lingual Document Similarity through Language-specific Concept ...Scalable Cross-lingual Document Similarity through Language-specific Concept ...
Scalable Cross-lingual Document Similarity through Language-specific Concept ...
 
Understanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational DatabasesUnderstanding Natural Language Queries over Relational Databases
Understanding Natural Language Queries over Relational Databases
 
A Panorama of Natural Language Processing
A Panorama of Natural Language ProcessingA Panorama of Natural Language Processing
A Panorama of Natural Language Processing
 
Approach to leverage Websites to APIs through Semantics
Approach to leverage Websites to APIs through SemanticsApproach to leverage Websites to APIs through Semantics
Approach to leverage Websites to APIs through Semantics
 
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)
LSI latent (par HATOUM Saria et DONGO ESCALANTE Irvin Franco)
 
What you Can Make Out of Linked Data
What you Can Make Out of Linked DataWhat you Can Make Out of Linked Data
What you Can Make Out of Linked Data
 
ESWC 2014 Tutorial part 3
ESWC 2014 Tutorial part 3ESWC 2014 Tutorial part 3
ESWC 2014 Tutorial part 3
 
Session 0.0 aussenac semanticsnl-pwebsem2017-v4
Session 0.0   aussenac semanticsnl-pwebsem2017-v4Session 0.0   aussenac semanticsnl-pwebsem2017-v4
Session 0.0 aussenac semanticsnl-pwebsem2017-v4
 

Kürzlich hochgeladen

Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 

Kürzlich hochgeladen (20)

Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 

Learning Multilingual Semantic Parsers for Question Answering over Linked Data - A comparison of neural and probabilistic graphical model architectures

  • 1. Learning Multilingual Semantic Parsers for 
 Question Answering over Linked Data A comparison of neural and probabilistic graphical model architectures PhD Dissertation Defense Talk March 2019 Sherzod Hakimov Semantic Computing Group, CITEC Bielefeld University
  • 2. Outline 1. Introduction 2. Motivation & Problem 3. Preliminaries 4. Dependency parse tree-based Semantic Parsing Approach 5. Evaluation of different architectural choices for “simple question” answering 6. Discussion 7. Conclusion 2
  • 7. 7 Give me the route to Jahnplatz What is Semantic Parsing? • mapping natural language sentence to a detailed meaning representation
  • 8. 8 Give me the route to Jahnplatz route($LOC, “Jahnplatz”) What is Semantic Parsing? • mapping natural language sentence to a detailed representation of meaning representation route(StartLocation, EndLocation)
  • 9. 9 Give me the route to Jahnplatz route($LOC, “Jahnplatz”) What is Semantic Parsing? • mapping natural language sentence to a detailed representation of meaning representation • meaning representation can be modelled using a formal language that
  • 10. 10 Give me the route to Jahnplatz route($LOC, “Jahnplatz”) What is Semantic Parsing? • mapping natural language sentence to a detailed representation of meaning representation • meaning representation can be modelled using a formal language, e.g. lambda calculus • an ontology with properties, classes, entities, etc. (route, create_calendar_event, set_alarm) • supports automated execution or reasoning
  • 11. 11 Give me the route to Jahnplatz Query Knowledge Base Answer Why do we need Semantic Parsers? route($LOC, “Jahnplatz”)
  • 12. 12 Give me the route to Jahnplatz Query Knowledge Base Answer Why do we need Semantic Parsers? route($LOC, “Jahnplatz”)
  • 13. Motivation • Building semantic parsers with application on Question Answering 13 Linked Data Cloud
  • 14. Motivation • Building semantic parsers with application on Question Answering • Building multilingual solutions that can be applied for multiple languages 14 Which German politicians were born in Bielefeld? Which metal has a liquid form? Welche deutschen Politiker wurden in Bielefeld geboren? Welches Metall hat eine flüssige Form? ¿Qué políticos alemanes nacieron en Bielefeld? ¿Qué metal tiene una forma líquida?
  • 15. Motivation • Building semantic parsers with application on Question Answering • Building multilingual solutions that can be extended for other languages • Comparison and evaluation of different model architectures 15
  • 16. Motivation • Building semantic parsers with application on Question Answering • Building multilingual solutions that can be extended for other languages • Comparison and evaluation of different model architectures • Highlight the challenges of building Question Answering systems 16
  • 17. • based on structured content from Wikipedia • more than 130 languages supported • 760 classes, 1105 object & 1622 data type properties • ca. 9 million resources 17
  • 19. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel) 19
  • 20. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel)Triple: dbr:Inferno_(novel) dbo:author dbr:Dan_Brown 20
  • 21. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel) Dan Brown is the author of Inferno Triple: Natural Language: dbr:Inferno_(novel) dbo:author dbr:Dan_Brown 21
  • 22. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel) Dan Brown is the author of Inferno Who is the author of Inferno?Natural Language: Question format dbr:Inferno_(novel) dbo:author dbr:Dan_BrownTriple: Natural Language: 22
  • 23. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel) Dan Brown is the author of Inferno dbr:Inferno_(novel) dbo:author dbr:Dan_BrownTriple: Natural Language: Who is the author of Inferno?Natural Language: SPARQL Query: Question format SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x} 23
  • 24. dbr:Dan_Brown dbo:author Question Answering on RDF Data dbr:Inferno_(novel)Who is the author of Inferno? Semantic Parser SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x} 24
  • 25. Research Questions How to map natural language phrases into knowledge base entries for multiple languages? Which linguistic resources can be used? 25 dbr:Dan_Brown dbo:author Who is the author of Inferno? dbr:Inferno_(novel) Who wrote Inferno? Who is the writer of Inferno? SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x}
  • 26. Research Questions How to map natural language phrases into knowledge base entries for multiple languages? Which linguistic resources can be used? 26 dbr:Dan_Brown dbo:author Who is the author of Inferno? dbr:Inferno_(novel) Who wrote Inferno? Who is the writer of Inferno? SELECT ?x WHERE {dbr:Inferno_(novel) dbo:author ?x} Lexical Gap: write -> dbo:author
  • 27. Research Questions How to disambiguate URIs when multiple candidates are retrieved from mapping natural language tokens into knowledge base entries? 27 When was Inferno released? SELECT ?x WHERE {dbr:Inferno_(novel) dbo:releaseDate ?x} dbr:Inferno_(2016_film) dbr:Inferno_(novel)
  • 28. Research Questions How to use syntactic information of a natural language question together with semantic representations of entries in a knowledge base? 28 Who wrote Inferno? dbr:Dan_Brown dbo:author dbr:Inferno_(novel) SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x } wrote
 (VERB) Who
 (PRON) Inferno
 (PROPN) nsubj dobj
  • 29. Research Questions What are the advantages and the disadvantages of a multilingual QA system vs. a monolingual system built for each language? 29 Who is the author of Inferno? dbr:Dan_Brown dbo:author dbr:Inferno_(novel) Wer ist der Autor von Inferno? ¿Quién es el autor de Inferno? SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x }
  • 30. Research Questions What effort is required to adapt our QA pipelines to another language? 30 Who is the author of Inferno? dbr:Dan_Brown dbo:author dbr:Inferno_(novel) Qui est l'auteur de Inferno? Infernoning muallifi kim? SELECT ?x WHERE { dbr:Inferno_(novel) dbo:author ?x }
  • 32. Preliminaries • Logical Form - DUDES, formalism for specifying meaning representations for dependency tree structures 32
  • 33. Preliminaries • Logical Form - DUDES, formalism for specifying meaning representations for dependency tree structures • Semantic Composition - acquiring the meaning representations using the syntax of questions 33
  • 34. Logical Form 34 • DUDES - Dependency-based Underspecified Discourse Representation Structures (Cimiano et al [1]) [1] Cimiano, P., 2009, Flexible semantic composition with DUDES. In Proceedings of the Eighth International Conference on Computational Semantics (pp. 272-276). Association for Computational Linguistics.
  • 35. Logical Form 35 • DUDES - Dependency-based Underspecified Discourse Representation Structures (Cimiano et al [1]) • Formalism for specifying meaning representation • Flexible semantic composition w.r.t order of application • Build on semantic dependencies e.g. suitable for working with dependency-based syntactic analysis
 [1] Cimiano, P., 2009, Flexible semantic composition with DUDES. In Proceedings of the Eighth International Conference on Computational Semantics (pp. 272-276). Association for Computational Linguistics.
  • 36. DUDES v : is the main variable vs : the projection variables l : is the label of the main DRS drs : is a DRS (Discourse Representation Structure) slots : is a set of semantic dependencies 36
  • 37. Semantic Composition with DUDES Who created Wikipedia? Input: a natural language question and its dependency parse tree 37
  • 38. Semantic Composition with DUDES Who created Wikipedia? Input: a natural language question and its dependency parse tree dbr:Wikipedia dbo:author ?x Output: a meaning representation based on certain domain 38
  • 39. Semantic Composition with DUDES Each node gets a pair of assignments: DUDES Type + Knowledge base ID Oracle 39
  • 40. Semantic Composition with DUDES - Bottom Up 40
  • 41. Semantic Composition with DUDES - Bottom Up 41 1 2
  • 42. Semantic Composition with DUDES - Bottom Up 42 2
  • 43. Semantic Composition with DUDES - Bottom Up 43 2
  • 44. Semantic Composition with DUDES - Bottom Up 44 2
  • 45. Semantic Composition with DUDES - Bottom Up 45 x
  • 47. Logical Form into SPARQL 47
  • 49. Dependency parse tree-based Semantic Parsing Approach • multilingual semantic parsing approach: English, German & Spanish [1] 49 [1] Hakimov S, Jebbara S, Cimiano P. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In Proceedings of the 16th International Semantic Web Conference (ISWC), 2017
  • 50. Dependency parse tree-based Semantic Parsing Approach • multilingual semantic parsing approach: English, German & Spanish [1] • uses language-independent dependency parse trees from Universal Dependencies 50 [1] Hakimov S, Jebbara S, Cimiano P. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In Proceedings of the 16th International Semantic Web Conference (ISWC), 2017
  • 51. Dependency parse tree-based Semantic Parsing Approach • multilingual semantic parsing approach: English, German & Spanish [1] • uses language-independent dependency parse trees from Universal Dependencies • combines different types of lexical information: DBpedia Ontology labels, the M-ATOLL[2] lexicon & word embeddings 51 [1] Hakimov S, Jebbara S, Cimiano P. “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data”. ISWC 2017 [2] Walter S, Unger C, and Cimiano P. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014 [3] Hakimov S, Walter S, Unger C, and Cimiano P. “Applying semantic parsing to question answering over linked data: Addressing the lexical gap”. NLDB 2015
  • 52. Dependency parse tree-based Semantic Parsing Approach Oracle SELECT ?x WHERE { dbr:Wikipedia dbo:author ?x. } Semantic Composition 52
  • 53. Dependency parse tree-based Semantic Parsing Approach Oracle SELECT ?x WHERE { dbr:Wikipedia dbo:author ?x. } Semantic Composition Structure Learning 53
  • 54. Dependency parse tree-based Semantic Parsing Approach • inference • factor graph model 54
  • 55. Inference • Metropolis-Hastings: exploring huge search space (ca. 10 million resources, 2000 properties) • Linking to Knowledge Base (L2KB) •objective : compare set of URIs to the expected set of URIs • Query Construction (QC) •objective : compare the constructed query to the expected query 55 Input: initial state
  • 56. L2KB Sampling Explore the edges and assign Knowledge Base IDs based on lemmas of nodes Inverted index: Ontology labels, lexicon from M-ATOLL & word embeddings 56
  • 57. L2KB Sampling Explore the edges and assign Knowledge Base IDs based on lemmas of nodes Check the triple pattern- ?x dbo:author dbr:Wikipedia : Slot 2, dbr:Wikipedia dbo:author ?x : Slot1 Inverted index: Ontology labels, lexicon from M-ATOLL & word embeddings 57
  • 58. 58
  • 59. 59
  • 60. 60
  • 61. QC Sampling Assign DUDES with Return Variable and KB ID to nodes and assign remaining slots 61
  • 63. Model Representation 63 Observed variables: dependency parse tree Hidden variables: KB IDs, slot, DUDE types
  • 64. Model Representation 64 Observed variables: dependency parse tree Hidden variables: KB IDs, slot, DUDE types
  • 65. Model Representation 65 Observed variables: dependency parse tree Hidden variables: KB IDs, slot, DUDE types Child_Node [POS: PROPN, DUDES: Resource] Parent_Node [POS: VERB, DUDES:Property] Sample Feature
  • 66. Evaluation Dataset: Question Answering over Linked Data (QALD), 6th challenge English, German, Spanish, Italian, French, Dutch, Romanian, Farsi 350 for train, 100 for test Unger, Christina, Axel-Cyrille Ngonga Ngomo, and Elena Cabrio (2016). “6th open challenge on question answering over linked data (qald-6)”. In: Semantic Web Evaluation Challenge. 66
  • 67. Evaluation DBP: lexicon from DBpedia Ontology & WordNet
 M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)
 Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013) Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014 Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013 67
  • 68. Evaluation DBP: lexicon from DBpedia Ontology & WordNet
 M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)
 Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013)
 Dict: manually defined lexicon Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014 Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013 68
  • 69. Evaluation DBP: lexicon from DBpedia Ontology & WordNet
 M-ATOLL: lexicon induced by the M-ATOLL (Walter et al. 2014)
 Embed: lexicon added using pre-trained word embeddings (Mikolov et al. 2013)
 Dict: manually defined lexicon Walter, Sebastian, Christina Unger, and Philipp Cimiano. “M-ATOLL: A Framework for the Lexicalization of Ontologies in Multiple Languages”. ISWC 2014 Mikolov, Tomas et al. “Distributed representations of words and phrases and their compositionality”. NIPS 2013 69
  • 71. Evaluation of different architectural choices for “simple question” answering 71
  • 72. Outline • SimpleQuestions dataset, 74k samples, Freebase data • Question: “Who wrote Mildred Pierced?” • Fact: mildred_pierced, book.written_work.author, stuart_kaminsky • Answer: mildred_pierced, book.written_work.author, ?x • Systematic comparison of different model architectures 72 Hakimov S, Jebbara S, Cimiano P. “Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases”. ICSC 2019
  • 73. Named Entity Recognition • Used by all models to predict the entity span • Character & word embeddings • Trained using weak supervision: inference is correct if the expected entity has been found 73
  • 74. Candidate Retrieval Candidate pairs: subject and predicate 74 Surface form frequencies
  • 75. Model1: BiLSTM-Softmax 75 Model2: BiLSTM-KB Model3: BiLSTM-Binary Model4: Fasttext [1] Architectures [1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, "Bag of Tricks for Efficient Text Classification", 2016, arxiv.org
  • 76. Model1: BiLSTM-Softmax 76 Model2: BiLSTM-KB Model3: BiLSTM-Binary Model4: Fasttext [1] Architectures [1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, "Bag of Tricks for Efficient Text Classification", 2016, arxiv.org
  • 77. Evaluation 77 Named Entity Linking Named Entity Recognition Predicate & Answer Prediction
  • 78. Evaluation 78 Named Entity Linking Named Entity Recognition 0,82 Predicate & Answer Prediction
  • 79. Evaluation 79 Named Entity Linking Named Entity Recognition 0,82 Predicate & Answer Prediction
  • 80. Evaluation 80 Named Entity Linking Named Entity Recognition 0,82 Predicate & Answer Prediction
  • 82. Discussion • Manual Effort • Syntax and Semantics • Multilinguality • Cross-domain Transferability • Training Data Size and Search Space 82
  • 83. Discussion 83 Systems Manual Effort Syntax & Semantics Multilinguality Cross-domain transferability Training Data & 
 Number of KB IDs CCG-based
 (Chapter 6) CCG combination rules
 manual lexicon • learned in tandem • CCG for syntax • lambda calculus for semantics manual effort is required manual effort is required 600 training instances 750 entities Dependency- based
 (Chapter 7) feature templates syntax is given DUDES as a formalism an adaptable solution • a dependency parser required. • e.g. biomedical domain 300 training instances <= 10 mil. entities
 >= 2000 predicates BiLSTM-Softmax
 (Chapter 8) - • word & char embed. for lexical & contextual info • semantics is limited to a single predicate and a subject entity an adaptable solution only word & char embed. an adaptable solution only word & char embed. >= 75K instances
 <= 2 mil. entities
  • 85. Research Questions 85 • Ontology lexicalisations, e.g. M-ATOLL (Walter et al. 2014) • Ontology labels, e.g. DBpedia labels • Dictionaries • WordNet synsets • Induced from contextual embeddings of words RQ1: How to map natural language phrases into knowledge base entries for multiple languages? Which linguistic resources can be used?
  • 86. Research Questions 86 • Supervised models with objective for disambiguation • CCG-based model • uses lexical and syntactic information as features • Dependency tree-based model • syntactic dependency between words, lexical similarity, ontology restrictions • Neural network-based model • ranking objective of predicates RQ2: How to disambiguate URIs when multiple candidates are retrieved from mapping natural language tokens into knowledge base entries?
  • 87. Research Questions 87 • Semantic Parsing • bottom-up composition • CCG-based model • learns the syntax and semantics together • Dependency tree-based model • learns composing semantics based on dependency trees RQ3: How to use syntactic information of a natural language question together with semantic representations of entries in a knowledge base?
  • 88. Research Questions 88 RQ4: What are the advantages and the disadvantages of a multilingual QA system vs. a monolingual system built for each language? • Advantages • Multilingual: broader coverage • Monolingual: higher performance, e.g. Xser (Xu et al. 2014) 0.7 F1 on QALD-4 • Disadvantages • Multilingual: lower performance, e.g. AMUSE 0.3 F1 on QALD-6 • Monolingual: need expertise, e.g. CCG rules, lexicon
  • 89. Research Questions 89 • CCG-based model • grammar rules, manually defined lexicon • language-specific • Dependency parse tree-based model • dependency parse tree generator • lexicon • Neural network-based model • depends on the training data RQ5: What effort is required to adapt our QA pipelines to another language?
  • 90. Conclusion • Address the lexical gap for QA systems • Incorporate ontology lexicalizations to reduce the lexical gap • Use Universal Dependencies to build language-independent QA pipeline • Multilingual semantic parsing for Question Answering • Evaluate different QA models under the certain conditions • Highlight importance of building blocks of a pipeline for a fair comparison 90
  • 92. GENLEX Barack Obama is married to Michelle Obama [1] Zettlemoyer, Luke S and Michael Collins (2005). “Learning to Map Sentences to Logical Form : Structured Classification with Probabilistic Categorial Grammars”. In: 21st Conference on Uncertainty in Artificial Intelligence [2] Hakimov, Sherzod et al. (2015). “Applying semantic parsing to question answering over linked data: Addressing the lexical gap”. In: International Conference on Applications of Natural Language to Information Systems 92
  • 93. CCG & GENLEX Rules 93
  • 94. Semantic Composition Barack Obama is married to Michelle Obama 94
  • 96. Lexicon During sampling, compute cosine similarity of words into Ontology labels of properties
 Vectors for multiple words are summed, e.g. V(population) + V(total) 96
  • 98. Dataset - GeoQuery 600 train, 280 test instances 98
  • 101. Dataset - SimpleQuestions Train: 75,910 Validation: 10,845 Test: 21,687 Total: 108,442 101
  • 102. Dataset Complexity Lexical Overlap, tokens exist in both 102
  • 103. Semantic Composition •recursively computing the meaning of each node from the meanings of its child nodes •build the meaning representation bottom-up ComposeSemantics(dependency-parse-tree) If parse-tree is a terminal node (word) then return an atomic lexical meaning for the word. Else For each child, subtreei, of parse-tree Create its MR by calling ComposeSemantics(subtreei) Return an MR by properly combining the resulting MRs for its children into an MR for the overall parse-tree. 103
  • 108. Model Representation 108 Observed variables: dependency parse tree Hidden variables: KB IDs, slot, DUDE types • States can be ranked by • objective score : compare to ground truth • model score: computed using feature weights • Training procedures • switch between model & objective score after every iteration
  • 111. Model1: BiLSTM-Softmax • Softmax layer that predicts predicates seen during training • Encoding layer: word & character • BiLSTM: two LSTM layers (backward, forward) 111
  • 112. Model2: BiLSTM-KB • Learn embedding of predicates in KB • Encoding layer: word & character • BiLSTM: two LSTM layers (backward, forward) • Output layer computes cosine similarity to all predicates and chooses the closest 112
  • 113. Model3: BiLSTM-Binary • Encoding layer: encodes input question with word & character embeddings • Encoding layer: encodes input predicate with word & character embeddings • Output layer: binary decision 113
  • 114. Model4: Fasttext • Document classification tool developed by Facebook* • Uses word & character embeddings • Softmax layer that predicts the expected predicate 114 * http://fasttext.cc
  • 116. 116 Generative Models -> computing joint probability distribution on p(y|x)
 HMM -> y_t depends on y_t-1 and x_t how output label y_t generates input vector x Discriminative Models -> computing conditional probability distribution over inputs x and outputs y
 CRF -> doesn’t have any limitation like that how feature vector x gets assignment y_t
  • 118. Manual Effort • CCG-based model • define CCG grammar rules, hand-crafted lexicon for domain independent phrases • Dependency parse tree-based model • feature functions • Neural network-based model (BiLSTM-Softmax) • not required 118
  • 119. Syntax and Semantics • CCG-based model • syntax and semantics is learned in tandem • CCG for syntax and the lambda calculus for semantics • syntax guides the semantics of the sentences • Dependency parse tree-based model • syntax is given and the semantics is learned • DUDES as a formalism for semantics, syntax is based on dependency trees from Universal Dependencies • Neural network-based model (BiLSTM-Softmax) • syntactic information is learned, e.g. word and character embeddings provide contextual information • semantics is based on a single subject and the predicate, simpler task 119
  • 120. Multilinguality • CCG-based model • CCG grammar rules needs to be extended • Dependency parse tree-based model • a multilingual solution • Neural network-based model (BiLSTM-Softmax) • can be adapted to other languages, e.g. word & characters as features 120
  • 121. Cross-domain Transferability • CCG-based model • manual effort is required: CCG rules, lexicon • Dependency parse tree-based model • dependency parse trees e.g. biomedical domain • Neural network-based model (BiLSTM-Softmax) • can be easily adapted 121
  • 122. Training Data Size and Search Space • CCG-based model • Dependency parse tree-based model • Neural network-based model (BiLSTM-Softmax) • heavily depends on the data 122