SlideShare a Scribd company logo
1 of 1
Download to read offline
HMM-based Artificial Designer for
Search Interface Segmentation
Ritu Khare, Yuan An, Il-Yeol Song
ACCESSING THE DEEP WEB

HMM: ARTIFICIAL DESIGNER

Deep Web: Data that exist on the Web but are not
returned by search engines through traditional crawling
and indexing.

An HMM (Hidden Markov Model) can act like a human designer
who has the ability to design an interface using acquired
knowledge and to determine (decode) the segment boundaries
and semantic labels of components.

Accessing Deep Web contents: The primary way to
access this data (by manually filling up HTML forms on
search interfaces ) is not scalable.
Hence, more sophisticated solutions, such as designing
meta-search engines or creating dynamic page
repositories, are required. A pre-requisite to these
solutions is an understanding of the search interfaces.
Interface Segmentation is an important portion of the
problem of search interface understanding.

INTERFACE SEGMENTATION

RESULTS
0.3

0.15

Knowledge of
Semantic Labels

TextTrivial

0.23
0.21

Segments &
Tagged
Components

DESIGNING

2-Layered
HMM

Search
Interface

0.21

0.59

Operand
Bag of
Components

0.44
0.16

Fig 2. Simulating a Human
Designer using HMMs

Attributename

0.54
0.08
0.89

0.09
Operator

DECODING

The designing process is similar to statistically choosing one
component from a bag of components (a superset of all possible
components) and placing it on the interface while keeping the
semantic role (attribute-name, operand, or operator) of the
component in mind. See Figure 2.

Fig 4. Learnt Topology of semantic labels

Semantic Label

Accuracy

Segment /Logical Attribute

86.05
86 05 %

Marker Range:

Operator

85.10 %

between

Operand

98.60 %

Attribute-name

90.11 %

and
e.g., between “D19Mit32” and “Tbx10”

cM Position:
between
e.g., “10.0 -40.0”
Fig 1. Segmented Interface
(segments marked by dotted lines)

While a user
is naturally trained to perform
g
,
g
segmentation, a machine is unable to “see” a segment
due to the following reasons:
1. The components that are visually close to each other
might be located very far apart in the HTML source
code.
2. A machine does not implicitly have any search
experience that can be leveraged to identify a
segment ‘ b
t ‘s boundary.
d
Research Question: How can we make a machine learn
how to segment an interface?

2-LAYERED HMM APPROACH
The problem of decoding is two-folded: 1) Segmentation, 2)
Assignment of semantic labels to components. Hence, a 2-layered
HMM is employed as shown in Figure 3. The first layer T-HMM
tags each component with appropriate semantic labels (attributeg
p
pp p
(
name, operator, and operand). The second layer S-HMM
segments the interface into logical attributes.
HTML
coded
Interfaces

T-HMM
Training
Interfaces

Manually
y
Tagged
Sequences

S-HMM
Manually
y
Segmented
Interfaces

Fig 3. 2-Layered HMM Architecture

EXPERIMENTATION
Data Set

200 interfaces from Biology Domain

Parsing

DOM-trees of components

Training

Maximum Likelihood Method

Testing

Viterbi Algorithm

Segmented
and Tagged
Interfaces

CONTRIBUTIONS
1 This approach outperforms LEX a contemporary
1.
LEX,
heuristic-based method, and achieves a 10%
improvement in segmentation accuracy.
2. This is the first work to apply HMMs on deep Web
search interfaces. HMMs helped in incorporating the
first-hand knowledge of the designer to perform
interface understanding.

FUTURE WORK
1. To recover the schema of deep Web databases by
extraction of finer details such as data type and
constraints of logical attribute.
2. To test this approach on interfaces from other
domains, given the diverse domain distribution of
the deep Web
3. To investigate the use of the use of Baum Welch
training algorithm to minimize the degree of
automation .

More Related Content

Viewers also liked

Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...
Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...
Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...William Kritsonis
 
6º Ideias na Laje - Apresentação 5.0 // Logotube
6º Ideias na Laje - Apresentação 5.0 // Logotube6º Ideias na Laje - Apresentação 5.0 // Logotube
6º Ideias na Laje - Apresentação 5.0 // LogotubeIdeias na Laje
 
2º Ideias na Laje Pitch - NetFraldas
2º Ideias na Laje Pitch - NetFraldas2º Ideias na Laje Pitch - NetFraldas
2º Ideias na Laje Pitch - NetFraldasIdeias na Laje
 
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARK
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARKSPICE MODEL of 8RHB_33uH_1.4A in SPICE PARK
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARKTsuyoshi Horigome
 
1988 a+a 200-146-alpha-sco
1988 a+a 200-146-alpha-sco1988 a+a 200-146-alpha-sco
1988 a+a 200-146-alpha-scoKees De Jager
 
Three newly discovered_globular_clusters_in_ngc6822
Three newly discovered_globular_clusters_in_ngc6822Three newly discovered_globular_clusters_in_ngc6822
Three newly discovered_globular_clusters_in_ngc6822Sérgio Sacani
 
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData Sheet
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData SheetIBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData Sheet
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData SheetIBM India Smarter Computing
 
12º Ideias na Laje - Apresentação 5.0 // Yeti
12º Ideias na Laje - Apresentação 5.0 // Yeti12º Ideias na Laje - Apresentação 5.0 // Yeti
12º Ideias na Laje - Apresentação 5.0 // YetiIdeias na Laje
 
Refiners Fire Presentation
Refiners Fire PresentationRefiners Fire Presentation
Refiners Fire Presentationryanklong
 
Battle Of The Bulge
Battle Of The BulgeBattle Of The Bulge
Battle Of The Bulgemjrybarski
 

Viewers also liked (16)

Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...
Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...
Dr. William Allan Kritsonis, Dissertation Chair for Elias Alex Torrez, Disser...
 
6º Ideias na Laje - Apresentação 5.0 // Logotube
6º Ideias na Laje - Apresentação 5.0 // Logotube6º Ideias na Laje - Apresentação 5.0 // Logotube
6º Ideias na Laje - Apresentação 5.0 // Logotube
 
Improving Interoperability of Text Mining Tools with BioC
Improving Interoperability of Text Mining Tools with BioCImproving Interoperability of Text Mining Tools with BioC
Improving Interoperability of Text Mining Tools with BioC
 
2º Ideias na Laje Pitch - NetFraldas
2º Ideias na Laje Pitch - NetFraldas2º Ideias na Laje Pitch - NetFraldas
2º Ideias na Laje Pitch - NetFraldas
 
Aa17043 11
Aa17043 11Aa17043 11
Aa17043 11
 
1106.2545v1
1106.2545v11106.2545v1
1106.2545v1
 
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARK
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARKSPICE MODEL of 8RHB_33uH_1.4A in SPICE PARK
SPICE MODEL of 8RHB_33uH_1.4A in SPICE PARK
 
1988 a+a 200-146-alpha-sco
1988 a+a 200-146-alpha-sco1988 a+a 200-146-alpha-sco
1988 a+a 200-146-alpha-sco
 
The Real Truth Behind SDO Collaboration
The Real Truth Behind SDO CollaborationThe Real Truth Behind SDO Collaboration
The Real Truth Behind SDO Collaboration
 
Summary to cv
Summary to cvSummary to cv
Summary to cv
 
Three newly discovered_globular_clusters_in_ngc6822
Three newly discovered_globular_clusters_in_ngc6822Three newly discovered_globular_clusters_in_ngc6822
Three newly discovered_globular_clusters_in_ngc6822
 
Versão 1.66
Versão 1.66Versão 1.66
Versão 1.66
 
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData Sheet
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData SheetIBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData Sheet
IBMSystem x3850 X5and x3950 X5 IBMSystems and TechnologyData Sheet
 
12º Ideias na Laje - Apresentação 5.0 // Yeti
12º Ideias na Laje - Apresentação 5.0 // Yeti12º Ideias na Laje - Apresentação 5.0 // Yeti
12º Ideias na Laje - Apresentação 5.0 // Yeti
 
Refiners Fire Presentation
Refiners Fire PresentationRefiners Fire Presentation
Refiners Fire Presentation
 
Battle Of The Bulge
Battle Of The BulgeBattle Of The Bulge
Battle Of The Bulge
 

Similar to HMM-based Artificial Designer for Search Interface Segmentation

An Empirical Study on Using Hidden Markov Models for Search Interface Segment...
An Empirical Study on Using Hidden Markov Models for Search Interface Segment...An Empirical Study on Using Hidden Markov Models for Search Interface Segment...
An Empirical Study on Using Hidden Markov Models for Search Interface Segment...The Children's Hospital of Philadelphia
 
Boilerplate removal and content
Boilerplate removal and contentBoilerplate removal and content
Boilerplate removal and contentIJCSEA Journal
 
Boilerplate Removal and Content Extraction from Dynamic Web Pages
Boilerplate Removal and Content Extraction from Dynamic Web PagesBoilerplate Removal and Content Extraction from Dynamic Web Pages
Boilerplate Removal and Content Extraction from Dynamic Web PagesIJCSEA Journal
 
Internet and Web Technology (CLASS-5) [HTML DOM]
Internet and Web Technology (CLASS-5) [HTML DOM] Internet and Web Technology (CLASS-5) [HTML DOM]
Internet and Web Technology (CLASS-5) [HTML DOM] Ayes Chinmay
 
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...IRJET Journal
 
Semi structure data extraction
Semi structure data extractionSemi structure data extraction
Semi structure data extractionR A Akerkar
 
E mine by V.DINESH KUMAR KSRCT
E mine by V.DINESH KUMAR KSRCTE mine by V.DINESH KUMAR KSRCT
E mine by V.DINESH KUMAR KSRCTdinesh2vasu
 
Taking browsers fuzzing new
Taking browsers fuzzing newTaking browsers fuzzing new
Taking browsers fuzzing newgeeksec80
 
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_level
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_levelDeep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_level
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_levelgeeksec80
 
AI and Web-Based Interactive College Enquiry Chatbot
AI and Web-Based Interactive College Enquiry ChatbotAI and Web-Based Interactive College Enquiry Chatbot
AI and Web-Based Interactive College Enquiry ChatbotIRJET Journal
 
Course_Documents
Course_DocumentsCourse_Documents
Course_DocumentsKaran Patil
 
Vision Based Deep Web data Extraction on Nested Query Result Records
Vision Based Deep Web data Extraction on Nested Query Result RecordsVision Based Deep Web data Extraction on Nested Query Result Records
Vision Based Deep Web data Extraction on Nested Query Result RecordsIJMER
 
Licence plate recognition using matlab programming
Licence plate recognition using matlab programming Licence plate recognition using matlab programming
Licence plate recognition using matlab programming somchaturvedi
 
Semantic Technolgies for the Internet of Things
Semantic Technolgies for the Internet of ThingsSemantic Technolgies for the Internet of Things
Semantic Technolgies for the Internet of ThingsPayamBarnaghi
 

Similar to HMM-based Artificial Designer for Search Interface Segmentation (20)

Two Layered HMMs for Search Interface Segmentation
Two Layered HMMs for Search Interface SegmentationTwo Layered HMMs for Search Interface Segmentation
Two Layered HMMs for Search Interface Segmentation
 
An Empirical Study on Using Hidden Markov Models for Search Interface Segment...
An Empirical Study on Using Hidden Markov Models for Search Interface Segment...An Empirical Study on Using Hidden Markov Models for Search Interface Segment...
An Empirical Study on Using Hidden Markov Models for Search Interface Segment...
 
Boilerplate removal and content
Boilerplate removal and contentBoilerplate removal and content
Boilerplate removal and content
 
Boilerplate Removal and Content Extraction from Dynamic Web Pages
Boilerplate Removal and Content Extraction from Dynamic Web PagesBoilerplate Removal and Content Extraction from Dynamic Web Pages
Boilerplate Removal and Content Extraction from Dynamic Web Pages
 
Internet and Web Technology (CLASS-5) [HTML DOM]
Internet and Web Technology (CLASS-5) [HTML DOM] Internet and Web Technology (CLASS-5) [HTML DOM]
Internet and Web Technology (CLASS-5) [HTML DOM]
 
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...
GENERATION OF HTML CODE AUTOMATICALLY USING MOCK-UP IMAGES WITH MACHINE LEARN...
 
Semi structure data extraction
Semi structure data extractionSemi structure data extraction
Semi structure data extraction
 
E mine by V.DINESH KUMAR KSRCT
E mine by V.DINESH KUMAR KSRCTE mine by V.DINESH KUMAR KSRCT
E mine by V.DINESH KUMAR KSRCT
 
8017 25 image mining
8017 25 image mining8017 25 image mining
8017 25 image mining
 
Taking browsers fuzzing new
Taking browsers fuzzing newTaking browsers fuzzing new
Taking browsers fuzzing new
 
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_level
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_levelDeep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_level
Deep sec 2012_rosario_valotta_-_taking_browsers_fuzzing_to_the_next_(dom)_level
 
AI and Web-Based Interactive College Enquiry Chatbot
AI and Web-Based Interactive College Enquiry ChatbotAI and Web-Based Interactive College Enquiry Chatbot
AI and Web-Based Interactive College Enquiry Chatbot
 
Course_Documents
Course_DocumentsCourse_Documents
Course_Documents
 
Vision Based Deep Web data Extraction on Nested Query Result Records
Vision Based Deep Web data Extraction on Nested Query Result RecordsVision Based Deep Web data Extraction on Nested Query Result Records
Vision Based Deep Web data Extraction on Nested Query Result Records
 
Lecture 01 - Chapter 1 (Part 01): Some basic concept of Operating System (OS)...
Lecture 01 - Chapter 1 (Part 01): Some basic concept of Operating System (OS)...Lecture 01 - Chapter 1 (Part 01): Some basic concept of Operating System (OS)...
Lecture 01 - Chapter 1 (Part 01): Some basic concept of Operating System (OS)...
 
Licence plate recognition using matlab programming
Licence plate recognition using matlab programming Licence plate recognition using matlab programming
Licence plate recognition using matlab programming
 
Webcomponents v2
Webcomponents v2Webcomponents v2
Webcomponents v2
 
Semantic Technolgies for the Internet of Things
Semantic Technolgies for the Internet of ThingsSemantic Technolgies for the Internet of Things
Semantic Technolgies for the Internet of Things
 
Ak4301197200
Ak4301197200Ak4301197200
Ak4301197200
 
Html
HtmlHtml
Html
 

Recently uploaded

New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxBkGupta21
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 

Recently uploaded (20)

New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptx
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 

HMM-based Artificial Designer for Search Interface Segmentation

  • 1. HMM-based Artificial Designer for Search Interface Segmentation Ritu Khare, Yuan An, Il-Yeol Song ACCESSING THE DEEP WEB HMM: ARTIFICIAL DESIGNER Deep Web: Data that exist on the Web but are not returned by search engines through traditional crawling and indexing. An HMM (Hidden Markov Model) can act like a human designer who has the ability to design an interface using acquired knowledge and to determine (decode) the segment boundaries and semantic labels of components. Accessing Deep Web contents: The primary way to access this data (by manually filling up HTML forms on search interfaces ) is not scalable. Hence, more sophisticated solutions, such as designing meta-search engines or creating dynamic page repositories, are required. A pre-requisite to these solutions is an understanding of the search interfaces. Interface Segmentation is an important portion of the problem of search interface understanding. INTERFACE SEGMENTATION RESULTS 0.3 0.15 Knowledge of Semantic Labels TextTrivial 0.23 0.21 Segments & Tagged Components DESIGNING 2-Layered HMM Search Interface 0.21 0.59 Operand Bag of Components 0.44 0.16 Fig 2. Simulating a Human Designer using HMMs Attributename 0.54 0.08 0.89 0.09 Operator DECODING The designing process is similar to statistically choosing one component from a bag of components (a superset of all possible components) and placing it on the interface while keeping the semantic role (attribute-name, operand, or operator) of the component in mind. See Figure 2. Fig 4. Learnt Topology of semantic labels Semantic Label Accuracy Segment /Logical Attribute 86.05 86 05 % Marker Range: Operator 85.10 % between Operand 98.60 % Attribute-name 90.11 % and e.g., between “D19Mit32” and “Tbx10” cM Position: between e.g., “10.0 -40.0” Fig 1. Segmented Interface (segments marked by dotted lines) While a user is naturally trained to perform g , g segmentation, a machine is unable to “see” a segment due to the following reasons: 1. The components that are visually close to each other might be located very far apart in the HTML source code. 2. A machine does not implicitly have any search experience that can be leveraged to identify a segment ‘ b t ‘s boundary. d Research Question: How can we make a machine learn how to segment an interface? 2-LAYERED HMM APPROACH The problem of decoding is two-folded: 1) Segmentation, 2) Assignment of semantic labels to components. Hence, a 2-layered HMM is employed as shown in Figure 3. The first layer T-HMM tags each component with appropriate semantic labels (attributeg p pp p ( name, operator, and operand). The second layer S-HMM segments the interface into logical attributes. HTML coded Interfaces T-HMM Training Interfaces Manually y Tagged Sequences S-HMM Manually y Segmented Interfaces Fig 3. 2-Layered HMM Architecture EXPERIMENTATION Data Set 200 interfaces from Biology Domain Parsing DOM-trees of components Training Maximum Likelihood Method Testing Viterbi Algorithm Segmented and Tagged Interfaces CONTRIBUTIONS 1 This approach outperforms LEX a contemporary 1. LEX, heuristic-based method, and achieves a 10% improvement in segmentation accuracy. 2. This is the first work to apply HMMs on deep Web search interfaces. HMMs helped in incorporating the first-hand knowledge of the designer to perform interface understanding. FUTURE WORK 1. To recover the schema of deep Web databases by extraction of finer details such as data type and constraints of logical attribute. 2. To test this approach on interfaces from other domains, given the diverse domain distribution of the deep Web 3. To investigate the use of the use of Baum Welch training algorithm to minimize the degree of automation .