SlideShare ist ein Scribd-Unternehmen logo
1 von 19
Downloaden Sie, um offline zu lesen
Multi-turn QA: A RNN Contextual Approach
to Intent Classification
for Goal-oriented Systems
Martino Mensio
Giuseppe Rizzo
Maurizio Morisio
HQA 2018 @ WWW2018
23 April 2018
Lyon, FR
General idea
QA and multi-turn interactions:
- Usually QA systems only work in single-turn
- Goal-oriented systems with dialog management (rules)
Idea: provide a dynamic - context based - sentence classification:
- shown in a Goal-oriented system
- can be extended to general QA systems
2
Background
3
Multi-turn interactions: example
4
Background: QA agents
complex interrogations
“List the movies whose
music composer’s
honorary title is BAFTA
Award for Best Film
Music”
5
complex knowledge one question
↓
one answer
Background: Goal-oriented agents
- main focus: not only questions, also actions
- limited search capabilities: fixed API set → fixed set of intents
- multi-turn bidirectional QA: missing parameters can be asked back
- KB content changes frequently
6
The problems of rule-based context management
7
The point of contact
8
The possible contexts
9
domain interaction user
Approach
10
Idea
Extend [1] by:
- detecting the change of intent
- capturing intent dependencies
- considering the agent words
11
[1] Liu, B. and Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and
slot filling. Proceedings of The 17th Annual Meeting of the International Speech Communication Association.
Approach: difference between
multi-turn and single-turn
12
Approach: multi-turn example
13
Experimentation
14
Dataset
15
Key-Value Retrieval [2]:
- 3 intent types
- 15 slot types
- sessions made of different turns
[2] Eric, M. and Manning, C. (2017). Key-value retrieval networks for task-oriented dialogue. SIGDIAL 2017: Session
on Natural Language Generation for Dialog Systems
#dialogues #user_turns #intent_change
training 2,425 6429 1583
validation 302 820 189
test 304 790 217
preprocessing:
1. move the intent from the session to
the single sentences
2. concatenate all the sessions
3. for each driver sentence, retrieve
inputs and outputs and build samples
Embeddings
Distributional Semantics [2]: words used in similar contexts have
similar meaning
[8] precomputed, 685k keys, 685k unique vectors
16
[2] Harris, Z. S. (1970). Distributional structure. In Papers in structural and transformational linguistics (pp.
775-794). Springer, Dordrecht.
[8] https://spacy.io/models/en
Results: multi-turn intent classification
17
approach
F1 epoch number
intent RNN agent words
1 ✓ LSTM ✓ 0.9987 7
2 ✓ LSTM ✘ 0.9987 8
3 ✓ GRU ✓ 0.9975 14
4 ✘ ✓ 0.9951 5
5 ✓ GRU ✘ 0.9585 9
6 [1]✘ ✘ 0.8524 8
7 CRF on pretrained word embeddings 0.7049 100
8 CRF on words 0.4976 100
[1] Liu, B. and Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot
filling. Proceedings of The 17th Annual Meeting of the International Speech Communication Association.
Conclusions
- understanding the sentences is a very important task in QA
- interaction context really matters for sentence classification
- future work
- entities
- hyperparameter optimization
- Knowledge usage, not only classification
18
The context of interaction can help QA systems
https://www.slideshare.net/MartinoMensio
https://twitter.com/MartinoMensio
19

Weitere ähnliche Inhalte

Ähnlich wie Multi-turn QA: A RNN Contextual Approach to Intent Classification for Goal-oriented Systems

By the Community & For the Community: A Deep Learning Approach to Assist Coll...
By the Community & For the Community: A Deep Learning Approach to Assist Coll...By the Community & For the Community: A Deep Learning Approach to Assist Coll...
By the Community & For the Community: A Deep Learning Approach to Assist Coll...
Chunyang Chen
 
Contributors wanted - Increasing diversity in your open source project (@k88h...
Contributors wanted - Increasing diversity in your open source project (@k88h...Contributors wanted - Increasing diversity in your open source project (@k88h...
Contributors wanted - Increasing diversity in your open source project (@k88h...
k88hudson
 
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
Lionel Briand
 
Designing collaborative processes for requirements
Designing collaborative processes for requirementsDesigning collaborative processes for requirements
Designing collaborative processes for requirements
RESGWorkshop
 
06 styles and_greenfield_design
06 styles and_greenfield_design06 styles and_greenfield_design
06 styles and_greenfield_design
Majong DevJfu
 

Ähnlich wie Multi-turn QA: A RNN Contextual Approach to Intent Classification for Goal-oriented Systems (20)

Conf 2012-empirikom3
Conf 2012-empirikom3Conf 2012-empirikom3
Conf 2012-empirikom3
 
Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...
Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...
Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...
 
Code Craftsmanship Checklist
Code Craftsmanship ChecklistCode Craftsmanship Checklist
Code Craftsmanship Checklist
 
Domain Driven Design: Made Easy employing Systemic Approach
Domain Driven Design: Made Easy employing Systemic ApproachDomain Driven Design: Made Easy employing Systemic Approach
Domain Driven Design: Made Easy employing Systemic Approach
 
By the Community & For the Community: A Deep Learning Approach to Assist Coll...
By the Community & For the Community: A Deep Learning Approach to Assist Coll...By the Community & For the Community: A Deep Learning Approach to Assist Coll...
By the Community & For the Community: A Deep Learning Approach to Assist Coll...
 
Contextualizing Rename Decisions using Refactorings and Commit Messages
Contextualizing Rename Decisions using Refactorings and Commit MessagesContextualizing Rename Decisions using Refactorings and Commit Messages
Contextualizing Rename Decisions using Refactorings and Commit Messages
 
Contributors wanted - Increasing diversity in your open source project (@k88h...
Contributors wanted - Increasing diversity in your open source project (@k88h...Contributors wanted - Increasing diversity in your open source project (@k88h...
Contributors wanted - Increasing diversity in your open source project (@k88h...
 
Quality, Cost, and Governance of Open Source Software
Quality, Cost, and Governance of Open Source SoftwareQuality, Cost, and Governance of Open Source Software
Quality, Cost, and Governance of Open Source Software
 
HCI 3e - Ch 7: Design rules
HCI 3e - Ch 7:  Design rulesHCI 3e - Ch 7:  Design rules
HCI 3e - Ch 7: Design rules
 
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
Analyzing Natural-Language Requirements: The Not-too-sexy and Yet Curiously D...
 
Dissertation defense slides on "Semantic Analysis for Improved Multi-document...
Dissertation defense slides on "Semantic Analysis for Improved Multi-document...Dissertation defense slides on "Semantic Analysis for Improved Multi-document...
Dissertation defense slides on "Semantic Analysis for Improved Multi-document...
 
Designing collaborative processes for requirements
Designing collaborative processes for requirementsDesigning collaborative processes for requirements
Designing collaborative processes for requirements
 
DeepPavlov 2019
DeepPavlov 2019DeepPavlov 2019
DeepPavlov 2019
 
06 styles and_greenfield_design
06 styles and_greenfield_design06 styles and_greenfield_design
06 styles and_greenfield_design
 
Measuring the usefulness of Knowledge Organization Systems in Information Ret...
Measuring the usefulness of Knowledge Organization Systems in Information Ret...Measuring the usefulness of Knowledge Organization Systems in Information Ret...
Measuring the usefulness of Knowledge Organization Systems in Information Ret...
 
Hindi language as a graphical user interface to relational database for tran...
Hindi language as a graphical user interface to relational  database for tran...Hindi language as a graphical user interface to relational  database for tran...
Hindi language as a graphical user interface to relational database for tran...
 
Defesa de doutorado - Leonardo Leite (USP)
Defesa de doutorado - Leonardo Leite (USP)Defesa de doutorado - Leonardo Leite (USP)
Defesa de doutorado - Leonardo Leite (USP)
 
11 Strategic Considerations for SharePoint Migrations
11 Strategic Considerations for SharePoint Migrations11 Strategic Considerations for SharePoint Migrations
11 Strategic Considerations for SharePoint Migrations
 
Endurant Ecosystems: Model-based Assessment of Resilience of Digital Business...
Endurant Ecosystems: Model-based Assessment of Resilience of Digital Business...Endurant Ecosystems: Model-based Assessment of Resilience of Digital Business...
Endurant Ecosystems: Model-based Assessment of Resilience of Digital Business...
 
Data mining, prediction and machine learning with Sitecore xDB
Data mining, prediction and machine learning with Sitecore xDBData mining, prediction and machine learning with Sitecore xDB
Data mining, prediction and machine learning with Sitecore xDB
 

Mehr von Martino Mensio

Mehr von Martino Mensio (6)

Towards a Cross-Article Narrative Comparison of News
Towards a Cross-Article Narrative Comparison of NewsTowards a Cross-Article Narrative Comparison of News
Towards a Cross-Article Narrative Comparison of News
 
Detecting subtle text manipulations
Detecting subtle text manipulationsDetecting subtle text manipulations
Detecting subtle text manipulations
 
News Source Credibility in the Eyes of Different Assessors
News Source Credibility in the Eyes of Different AssessorsNews Source Credibility in the Eyes of Different Assessors
News Source Credibility in the Eyes of Different Assessors
 
A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling
A Multi-layer LSTM-based Approach for Robot Command Interaction ModelingA Multi-layer LSTM-based Approach for Robot Command Interaction Modeling
A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling
 
The Rise of Emotion-aware Conversational Agents: Threats in Digital Emotions
The Rise of Emotion-aware Conversational Agents: Threats in Digital EmotionsThe Rise of Emotion-aware Conversational Agents: Threats in Digital Emotions
The Rise of Emotion-aware Conversational Agents: Threats in Digital Emotions
 
Deep Learning per la Comprensione del Linguaggio Naturale - HKN
Deep Learning per la Comprensione del Linguaggio Naturale - HKNDeep Learning per la Comprensione del Linguaggio Naturale - HKN
Deep Learning per la Comprensione del Linguaggio Naturale - HKN
 

Kürzlich hochgeladen

Seismic Method Estimate velocity from seismic data.pptx
Seismic Method Estimate velocity from seismic  data.pptxSeismic Method Estimate velocity from seismic  data.pptx
Seismic Method Estimate velocity from seismic data.pptx
AlMamun560346
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
Sérgio Sacani
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
Areesha Ahmad
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
gindu3009
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Sérgio Sacani
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
ssuser79fe74
 

Kürzlich hochgeladen (20)

CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Seismic Method Estimate velocity from seismic data.pptx
Seismic Method Estimate velocity from seismic  data.pptxSeismic Method Estimate velocity from seismic  data.pptx
Seismic Method Estimate velocity from seismic data.pptx
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
 
American Type Culture Collection (ATCC).pptx
American Type Culture Collection (ATCC).pptxAmerican Type Culture Collection (ATCC).pptx
American Type Culture Collection (ATCC).pptx
 
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxCOST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verifiedConnaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 

Multi-turn QA: A RNN Contextual Approach to Intent Classification for Goal-oriented Systems

  • 1. Multi-turn QA: A RNN Contextual Approach to Intent Classification for Goal-oriented Systems Martino Mensio Giuseppe Rizzo Maurizio Morisio HQA 2018 @ WWW2018 23 April 2018 Lyon, FR
  • 2. General idea QA and multi-turn interactions: - Usually QA systems only work in single-turn - Goal-oriented systems with dialog management (rules) Idea: provide a dynamic - context based - sentence classification: - shown in a Goal-oriented system - can be extended to general QA systems 2
  • 5. Background: QA agents complex interrogations “List the movies whose music composer’s honorary title is BAFTA Award for Best Film Music” 5 complex knowledge one question ↓ one answer
  • 6. Background: Goal-oriented agents - main focus: not only questions, also actions - limited search capabilities: fixed API set → fixed set of intents - multi-turn bidirectional QA: missing parameters can be asked back - KB content changes frequently 6
  • 7. The problems of rule-based context management 7
  • 8. The point of contact 8
  • 11. Idea Extend [1] by: - detecting the change of intent - capturing intent dependencies - considering the agent words 11 [1] Liu, B. and Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of The 17th Annual Meeting of the International Speech Communication Association.
  • 15. Dataset 15 Key-Value Retrieval [2]: - 3 intent types - 15 slot types - sessions made of different turns [2] Eric, M. and Manning, C. (2017). Key-value retrieval networks for task-oriented dialogue. SIGDIAL 2017: Session on Natural Language Generation for Dialog Systems #dialogues #user_turns #intent_change training 2,425 6429 1583 validation 302 820 189 test 304 790 217 preprocessing: 1. move the intent from the session to the single sentences 2. concatenate all the sessions 3. for each driver sentence, retrieve inputs and outputs and build samples
  • 16. Embeddings Distributional Semantics [2]: words used in similar contexts have similar meaning [8] precomputed, 685k keys, 685k unique vectors 16 [2] Harris, Z. S. (1970). Distributional structure. In Papers in structural and transformational linguistics (pp. 775-794). Springer, Dordrecht. [8] https://spacy.io/models/en
  • 17. Results: multi-turn intent classification 17 approach F1 epoch number intent RNN agent words 1 ✓ LSTM ✓ 0.9987 7 2 ✓ LSTM ✘ 0.9987 8 3 ✓ GRU ✓ 0.9975 14 4 ✘ ✓ 0.9951 5 5 ✓ GRU ✘ 0.9585 9 6 [1]✘ ✘ 0.8524 8 7 CRF on pretrained word embeddings 0.7049 100 8 CRF on words 0.4976 100 [1] Liu, B. and Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of The 17th Annual Meeting of the International Speech Communication Association.
  • 18. Conclusions - understanding the sentences is a very important task in QA - interaction context really matters for sentence classification - future work - entities - hyperparameter optimization - Knowledge usage, not only classification 18
  • 19. The context of interaction can help QA systems https://www.slideshare.net/MartinoMensio https://twitter.com/MartinoMensio 19