SlideShare uma empresa Scribd logo
1 de 14
Question Answering on
Romanian, English and
French Languages
„„Al. I. Cuza” University of IaAl. I. Cuza” University of Ia ssi, Romi, Romaaniania
Faculty of Computer ScienceFaculty of Computer Science
 Introduction
 System components
◦ Questions analysis
◦ Index creation and information retrieval
◦ Answer extraction
 Results
 Application of QA system
◦ eLearning
◦ Robotics
◦ CriES 2010
 Conclusions
 Our group participate in CLEF exercises from 2006:
◦ 2006 – Ro–En (English collection) – 9.47% right answers
◦ 2007 – Ro–Ro (Romanian Wikipedia) – 12 %
◦ 2008 – Ro–Ro (Romanian Wikipedia) – 31 %
◦ 2009 – Ro–Ro, En–En (JRC-Acquis) – 47.2 % (48.6%)
◦ 2010 – Ro-Ro, En-En, Fr-Fr (JRC-Acquis, Europarl) – 47.5%
(42.5%, 27 %)
Lucene
queries
Lucene
Index
Question analysis:
- Tokenization & lemmatization
- Focus, keywords and names
entities identification
- Question classification
JRC-Acquis
corpus
Initial
questions
Information
Retrieval
Relevant
snippets
Romanian
Grammar
Definition Answer
Extraction
Reason Answer
Extraction
Other Answer
Extraction
Final
Answers
EUROPARL
corpus
Q1: What percentage of people in Italy relies on television for
information?
<q q_id="0001" source_lang="EN" target_lang="RO">
<string>Ce procent al populaţiei din Italia contează pe televiziune
pentru a obţine informaţii</string>
<focus>procent</focus>
<verb>contează obţine</verb>
<noun>populaţiei televiziune informaţii</noun>
<nameEntities>Italia</nameEntities>
<luceneQuery>procent~0.7 populaţiei~0.7 Italia^3 (contează^2
conta) televiziune~0.7 obţine informaţii~0.7 </luceneQuery>
<questionType>FACTOID</questionType> ~ 40 patterns
<answerType>MEASURE</answerType> ~ 30 patterns
</q>
 We used Lucene and we have created two
indexes, one at paragraph level and one at
document level
 Using the Lucene queries and the indexes we
used the Lucene search engine to extract a
ranked list of snippets for every question as
possible answer candidates
 Depend by Lucene score and additional we built
special modules to extract answers for questions of
type DEFINITION, REASON-PURPOSE,
PROCEDURE, OPINION
 Two thresholds values
◦ A higher one - in this case, the system offers many NOA
answers – RA is affected, but c@1 is higher
◦ A lower one – in this case we offer only a few NOA
answers – RA is higher, but c@1 is lower
RO-RO EN-EN FR-FR
answered right 95 102 85 78 54 47
answered wrong 74 93 98 99 124 153
total answered 169 195 183 177 178 200
unanswered right 0 0 0 0 0 0
unanswered
wrong
0 0 0 0 0 0
unanswered
empty
31 5 17 23 22 0
total unanswered 31 5 17 23 22 0
c@1 measure 0.55 0.42 0.46 0.43 0.30 0.24
 eLearning – fast answer for ~30% questions
 Robotics – communication
 CriES 2010 – identify experts on Yahoo!
Answers
Similar questions Answer Ok?
Exista aplicatii in care folosirea
Design Patterns-urilor sa nu fie
eficienta?
Evident (de exemplu un program Hello World)... Go
La ce altceva design pattrenurile ar
putea fi aplicate?
Gasirea solutiei la o problema, crearea unui limbaj de
programator avansat, in scrierea documentatiei, in
discutii cu colegii de la o firma de software.
Go
Care este diferenta dintre pattern si o
expresie (idiom) de codare.
Nu am auzit de expresia idiom de codare, dar pare
ceva particular, pe cand design pattern-ul este
general...
Go
Care este diferenta dintre pattern si
clase.
Un design pattern este o solutie la o problema si prin
urmare este compusa dintr-o ierarhie de clase intre
care avem relatii.
Go
Este design pattern-ul diferit de
pattern? De ce a fost ales acest nume?
Design pattern-ul este un pattern in domeniul
ingineriei software. Nu stiu de ce a fost ales acest
nume.... :)
Go
Folosim Design Patterns in aceeasi
aplicatie sau le folosim in aplicatii
diferite?
In aceeasi aplicatie. Go
Ce este un design pattern? In primul rand: un nume, o problema si o solutie Go
Questions Answer Priority Status Details
La ce se folosesc design
pattern-urile?
normal
nevoieN
eaparat Go
Raspunde la intrebare
Raspuns
Go
Exception handlingul in
Java poate fi considerat o
aplicatie a Decorator
pattern?
urgent
nevoieN
eaparat
Go
Raspunde la intrebare
Raspuns
Go
Exista aplicatii in care
folosirea Design Patterns-
urilor sa nu fie eficienta?
Evident (de exemplu un program
Hello World)...
normal doarAsa
La ce altceva design
Gasirea solutiei la o problema, crearea
unui limbaj de programator avansat, in saAfluM
 With Swoogle we extend the knowledge base
 The ontologies returned are then converted to AIML
format and saved in the robot’s memory
Initial
digraph
Initial Yahoo!answers collections
en fr ge sp
Eliminate stop
words
Domains
keywords
Initial users
questions
Eliminate stop
words
Questions
keywords
Relevant words for
questions
Relevant words for
domains
Similarity
score between
questions and
domains
Run 2 Run 1Run 0
 UAIC QA system evolved over time (from 9 % in
2006 at 47.5 % in 2010)
 The main problem is related to quality and quantity of
Romanian resources involved
 In present we are concerned with using of QA
components in other applications in order to improve
their capabilities
Question Answering on Romanian, English and French Languages

Mais conteúdo relacionado

Semelhante a Question Answering on Romanian, English and French Languages

Continuous Deployment and Testing Workshop from Better Software West
Continuous Deployment and Testing Workshop from Better Software WestContinuous Deployment and Testing Workshop from Better Software West
Continuous Deployment and Testing Workshop from Better Software WestCory Foy
 
IRJET- Semantic Question Matching
IRJET- Semantic Question MatchingIRJET- Semantic Question Matching
IRJET- Semantic Question MatchingIRJET Journal
 
Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)evabl444
 
Répondre à la question automatique avec le web
Répondre à la question automatique avec le webRépondre à la question automatique avec le web
Répondre à la question automatique avec le webAhmed Hammami
 
VOC real world enterprise needs
VOC real world enterprise needsVOC real world enterprise needs
VOC real world enterprise needsIvan Berlocher
 
Boost Your Base Bootcamp - [Online & Offline] In Bangla
Boost Your Base Bootcamp - [Online & Offline] In BanglaBoost Your Base Bootcamp - [Online & Offline] In Bangla
Boost Your Base Bootcamp - [Online & Offline] In BanglaStack Learner
 
Question Focus Recognition in Question Answering Systems
Question Focus Recognition in Question  Answering Systems Question Focus Recognition in Question  Answering Systems
Question Focus Recognition in Question Answering Systems Waheeb Ahmed
 
Answer Selection and Validation for Arabic Questions
Answer Selection and Validation for Arabic QuestionsAnswer Selection and Validation for Arabic Questions
Answer Selection and Validation for Arabic QuestionsAhmed Magdy Ezzeldin, MSc.
 
When develpment met test(shift left testing)
When develpment met test(shift left testing)When develpment met test(shift left testing)
When develpment met test(shift left testing)SangIn Choung
 
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language ModelsDataScienceConferenc1
 
Creativity vs Best Practices
Creativity vs Best PracticesCreativity vs Best Practices
Creativity vs Best PracticesSupun Dissanayake
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.pptbutest
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGIJwest
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGdannyijwest
 
[2017/2018] RESEARCH in software engineering
[2017/2018] RESEARCH in software engineering[2017/2018] RESEARCH in software engineering
[2017/2018] RESEARCH in software engineeringIvano Malavolta
 
Aspiring Minds | Automata
Aspiring Minds | Automata Aspiring Minds | Automata
Aspiring Minds | Automata Aspiring Minds
 
[2016/2017] RESEARCH in software engineering
[2016/2017] RESEARCH in software engineering[2016/2017] RESEARCH in software engineering
[2016/2017] RESEARCH in software engineeringIvano Malavolta
 

Semelhante a Question Answering on Romanian, English and French Languages (20)

Continuous Deployment and Testing Workshop from Better Software West
Continuous Deployment and Testing Workshop from Better Software WestContinuous Deployment and Testing Workshop from Better Software West
Continuous Deployment and Testing Workshop from Better Software West
 
IRJET- Semantic Question Matching
IRJET- Semantic Question MatchingIRJET- Semantic Question Matching
IRJET- Semantic Question Matching
 
Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)Experimenting with eXtreme Design (EKAW2010)
Experimenting with eXtreme Design (EKAW2010)
 
Répondre à la question automatique avec le web
Répondre à la question automatique avec le webRépondre à la question automatique avec le web
Répondre à la question automatique avec le web
 
VOC real world enterprise needs
VOC real world enterprise needsVOC real world enterprise needs
VOC real world enterprise needs
 
The terminology of methodology
The terminology of methodologyThe terminology of methodology
The terminology of methodology
 
Boost Your Base Bootcamp - [Online & Offline] In Bangla
Boost Your Base Bootcamp - [Online & Offline] In BanglaBoost Your Base Bootcamp - [Online & Offline] In Bangla
Boost Your Base Bootcamp - [Online & Offline] In Bangla
 
Question Focus Recognition in Question Answering Systems
Question Focus Recognition in Question  Answering Systems Question Focus Recognition in Question  Answering Systems
Question Focus Recognition in Question Answering Systems
 
Answer Selection and Validation for Arabic Questions
Answer Selection and Validation for Arabic QuestionsAnswer Selection and Validation for Arabic Questions
Answer Selection and Validation for Arabic Questions
 
When develpment met test(shift left testing)
When develpment met test(shift left testing)When develpment met test(shift left testing)
When develpment met test(shift left testing)
 
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models
[DSC Europe 23] Dmitry Ustalov - Design and Evaluation of Large Language Models
 
Creativity vs Best Practices
Creativity vs Best PracticesCreativity vs Best Practices
Creativity vs Best Practices
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
MLlecture1.ppt
MLlecture1.pptMLlecture1.ppt
MLlecture1.ppt
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
 
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERINGEVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
EVALUATION OF SINGLE-SPAN MODELS ON EXTRACTIVE MULTI-SPAN QUESTION-ANSWERING
 
[2017/2018] RESEARCH in software engineering
[2017/2018] RESEARCH in software engineering[2017/2018] RESEARCH in software engineering
[2017/2018] RESEARCH in software engineering
 
Aspiring Minds | Automata
Aspiring Minds | Automata Aspiring Minds | Automata
Aspiring Minds | Automata
 
Cser13.ppt
Cser13.pptCser13.ppt
Cser13.ppt
 
[2016/2017] RESEARCH in software engineering
[2016/2017] RESEARCH in software engineering[2016/2017] RESEARCH in software engineering
[2016/2017] RESEARCH in software engineering
 

Mais de Faculty of Computer Science

Using Artificial Intelligence in Software Engineering
Using Artificial Intelligence in Software EngineeringUsing Artificial Intelligence in Software Engineering
Using Artificial Intelligence in Software EngineeringFaculty of Computer Science
 
Eye and Voice Control for an Augmented Reality Cooking Experience
Eye and Voice Control for an Augmented Reality Cooking ExperienceEye and Voice Control for an Augmented Reality Cooking Experience
Eye and Voice Control for an Augmented Reality Cooking ExperienceFaculty of Computer Science
 
Exploiting Social Networks. Technological Trends
Exploiting Social Networks. Technological TrendsExploiting Social Networks. Technological Trends
Exploiting Social Networks. Technological TrendsFaculty of Computer Science
 
Using opinion mining techniques for early crisis detection
Using opinion mining techniques for early crisis detectionUsing opinion mining techniques for early crisis detection
Using opinion mining techniques for early crisis detectionFaculty of Computer Science
 
I See You, You Can't See Me: On People's Perception About Surveillance In Po...
I See You, You Can't See Me: On People's Perception About Surveillance In Po...I See You, You Can't See Me: On People's Perception About Surveillance In Po...
I See You, You Can't See Me: On People's Perception About Surveillance In Po...Faculty of Computer Science
 
Question Answering for Machine Reading Evaluation on Romanian and English
Question Answering for Machine Reading Evaluation on Romanian and EnglishQuestion Answering for Machine Reading Evaluation on Romanian and English
Question Answering for Machine Reading Evaluation on Romanian and EnglishFaculty of Computer Science
 
Recovering Diacritics using Wikipedia and Google
Recovering Diacritics using Wikipedia and GoogleRecovering Diacritics using Wikipedia and Google
Recovering Diacritics using Wikipedia and GoogleFaculty of Computer Science
 
Hypothesis Transformation and Semantic Variability Rules Used in RTE
Hypothesis Transformation and Semantic Variability Rules Used in RTEHypothesis Transformation and Semantic Variability Rules Used in RTE
Hypothesis Transformation and Semantic Variability Rules Used in RTEFaculty of Computer Science
 
Improving a Question Answering System for Romanian Using Textual Entailment
Improving a Question Answering System for Romanian Using Textual EntailmentImproving a Question Answering System for Romanian Using Textual Entailment
Improving a Question Answering System for Romanian Using Textual EntailmentFaculty of Computer Science
 
A Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual EntailmentA Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual EntailmentFaculty of Computer Science
 
Formalizing Peer-to-Peer Systems based on Content Addressable Network
Formalizing Peer-to-Peer Systems based on Content Addressable NetworkFormalizing Peer-to-Peer Systems based on Content Addressable Network
Formalizing Peer-to-Peer Systems based on Content Addressable NetworkFaculty of Computer Science
 

Mais de Faculty of Computer Science (19)

Using Artificial Intelligence in Software Engineering
Using Artificial Intelligence in Software EngineeringUsing Artificial Intelligence in Software Engineering
Using Artificial Intelligence in Software Engineering
 
Eye and Voice Control for an Augmented Reality Cooking Experience
Eye and Voice Control for an Augmented Reality Cooking ExperienceEye and Voice Control for an Augmented Reality Cooking Experience
Eye and Voice Control for an Augmented Reality Cooking Experience
 
Learn Chemistry with Augmented Reality
Learn Chemistry with Augmented RealityLearn Chemistry with Augmented Reality
Learn Chemistry with Augmented Reality
 
Exploiting Social Networks. Technological Trends
Exploiting Social Networks. Technological TrendsExploiting Social Networks. Technological Trends
Exploiting Social Networks. Technological Trends
 
Augmented Reality in Education
Augmented Reality in EducationAugmented Reality in Education
Augmented Reality in Education
 
Diversification in an Image Retrieval System
Diversification in an Image Retrieval SystemDiversification in an Image Retrieval System
Diversification in an Image Retrieval System
 
Using opinion mining techniques for early crisis detection
Using opinion mining techniques for early crisis detectionUsing opinion mining techniques for early crisis detection
Using opinion mining techniques for early crisis detection
 
Augmented reality
Augmented realityAugmented reality
Augmented reality
 
I See You, You Can't See Me: On People's Perception About Surveillance In Po...
I See You, You Can't See Me: On People's Perception About Surveillance In Po...I See You, You Can't See Me: On People's Perception About Surveillance In Po...
I See You, You Can't See Me: On People's Perception About Surveillance In Po...
 
Named Entity Recognition for Romanian
Named Entity Recognition for RomanianNamed Entity Recognition for Romanian
Named Entity Recognition for Romanian
 
Question Answering for Machine Reading Evaluation on Romanian and English
Question Answering for Machine Reading Evaluation on Romanian and EnglishQuestion Answering for Machine Reading Evaluation on Romanian and English
Question Answering for Machine Reading Evaluation on Romanian and English
 
Identify Experts from a Domain of Interest
Identify Experts from a Domain of Interest Identify Experts from a Domain of Interest
Identify Experts from a Domain of Interest
 
Recovering Diacritics using Wikipedia and Google
Recovering Diacritics using Wikipedia and GoogleRecovering Diacritics using Wikipedia and Google
Recovering Diacritics using Wikipedia and Google
 
UAIC Participation at RTE4
UAIC Participation at RTE4UAIC Participation at RTE4
UAIC Participation at RTE4
 
Hypothesis Transformation and Semantic Variability Rules Used in RTE
Hypothesis Transformation and Semantic Variability Rules Used in RTEHypothesis Transformation and Semantic Variability Rules Used in RTE
Hypothesis Transformation and Semantic Variability Rules Used in RTE
 
Improving a Question Answering System for Romanian Using Textual Entailment
Improving a Question Answering System for Romanian Using Textual EntailmentImproving a Question Answering System for Romanian Using Textual Entailment
Improving a Question Answering System for Romanian Using Textual Entailment
 
A Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual EntailmentA Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual Entailment
 
Graph Coloring using Peer-to-Peer Networks
Graph Coloring using Peer-to-Peer NetworksGraph Coloring using Peer-to-Peer Networks
Graph Coloring using Peer-to-Peer Networks
 
Formalizing Peer-to-Peer Systems based on Content Addressable Network
Formalizing Peer-to-Peer Systems based on Content Addressable NetworkFormalizing Peer-to-Peer Systems based on Content Addressable Network
Formalizing Peer-to-Peer Systems based on Content Addressable Network
 

Último

2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch TuesdayIvanti
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality AssuranceInflectra
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
Abdul Kader Baba- Managing Cybersecurity Risks and Compliance Requirements i...
Abdul Kader Baba- Managing Cybersecurity Risks  and Compliance Requirements i...Abdul Kader Baba- Managing Cybersecurity Risks  and Compliance Requirements i...
Abdul Kader Baba- Managing Cybersecurity Risks and Compliance Requirements i...itnewsafrica
 
Generative AI - Gitex v1Generative AI - Gitex v1.pptx
Generative AI - Gitex v1Generative AI - Gitex v1.pptxGenerative AI - Gitex v1Generative AI - Gitex v1.pptx
Generative AI - Gitex v1Generative AI - Gitex v1.pptxfnnc6jmgwh
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesKari Kakkonen
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
UiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPathCommunity
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...Wes McKinney
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfNeo4j
 
Zeshan Sattar- Assessing the skill requirements and industry expectations for...
Zeshan Sattar- Assessing the skill requirements and industry expectations for...Zeshan Sattar- Assessing the skill requirements and industry expectations for...
Zeshan Sattar- Assessing the skill requirements and industry expectations for...itnewsafrica
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfpanagenda
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
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
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsNathaniel Shimoni
 

Último (20)

2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch Tuesday
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
Abdul Kader Baba- Managing Cybersecurity Risks and Compliance Requirements i...
Abdul Kader Baba- Managing Cybersecurity Risks  and Compliance Requirements i...Abdul Kader Baba- Managing Cybersecurity Risks  and Compliance Requirements i...
Abdul Kader Baba- Managing Cybersecurity Risks and Compliance Requirements i...
 
Generative AI - Gitex v1Generative AI - Gitex v1.pptx
Generative AI - Gitex v1Generative AI - Gitex v1.pptxGenerative AI - Gitex v1Generative AI - Gitex v1.pptx
Generative AI - Gitex v1Generative AI - Gitex v1.pptx
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examples
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
UiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to HeroUiPath Community: Communication Mining from Zero to Hero
UiPath Community: Communication Mining from Zero to Hero
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
Zeshan Sattar- Assessing the skill requirements and industry expectations for...
Zeshan Sattar- Assessing the skill requirements and industry expectations for...Zeshan Sattar- Assessing the skill requirements and industry expectations for...
Zeshan Sattar- Assessing the skill requirements and industry expectations for...
 
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdfSo einfach geht modernes Roaming fuer Notes und Nomad.pdf
So einfach geht modernes Roaming fuer Notes und Nomad.pdf
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
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
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directions
 

Question Answering on Romanian, English and French Languages

  • 1. Question Answering on Romanian, English and French Languages „„Al. I. Cuza” University of IaAl. I. Cuza” University of Ia ssi, Romi, Romaaniania Faculty of Computer ScienceFaculty of Computer Science
  • 2.  Introduction  System components ◦ Questions analysis ◦ Index creation and information retrieval ◦ Answer extraction  Results  Application of QA system ◦ eLearning ◦ Robotics ◦ CriES 2010  Conclusions
  • 3.  Our group participate in CLEF exercises from 2006: ◦ 2006 – Ro–En (English collection) – 9.47% right answers ◦ 2007 – Ro–Ro (Romanian Wikipedia) – 12 % ◦ 2008 – Ro–Ro (Romanian Wikipedia) – 31 % ◦ 2009 – Ro–Ro, En–En (JRC-Acquis) – 47.2 % (48.6%) ◦ 2010 – Ro-Ro, En-En, Fr-Fr (JRC-Acquis, Europarl) – 47.5% (42.5%, 27 %)
  • 4. Lucene queries Lucene Index Question analysis: - Tokenization & lemmatization - Focus, keywords and names entities identification - Question classification JRC-Acquis corpus Initial questions Information Retrieval Relevant snippets Romanian Grammar Definition Answer Extraction Reason Answer Extraction Other Answer Extraction Final Answers EUROPARL corpus
  • 5. Q1: What percentage of people in Italy relies on television for information? <q q_id="0001" source_lang="EN" target_lang="RO"> <string>Ce procent al populaţiei din Italia contează pe televiziune pentru a obţine informaţii</string> <focus>procent</focus> <verb>contează obţine</verb> <noun>populaţiei televiziune informaţii</noun> <nameEntities>Italia</nameEntities> <luceneQuery>procent~0.7 populaţiei~0.7 Italia^3 (contează^2 conta) televiziune~0.7 obţine informaţii~0.7 </luceneQuery> <questionType>FACTOID</questionType> ~ 40 patterns <answerType>MEASURE</answerType> ~ 30 patterns </q>
  • 6.  We used Lucene and we have created two indexes, one at paragraph level and one at document level  Using the Lucene queries and the indexes we used the Lucene search engine to extract a ranked list of snippets for every question as possible answer candidates
  • 7.  Depend by Lucene score and additional we built special modules to extract answers for questions of type DEFINITION, REASON-PURPOSE, PROCEDURE, OPINION  Two thresholds values ◦ A higher one - in this case, the system offers many NOA answers – RA is affected, but c@1 is higher ◦ A lower one – in this case we offer only a few NOA answers – RA is higher, but c@1 is lower
  • 8. RO-RO EN-EN FR-FR answered right 95 102 85 78 54 47 answered wrong 74 93 98 99 124 153 total answered 169 195 183 177 178 200 unanswered right 0 0 0 0 0 0 unanswered wrong 0 0 0 0 0 0 unanswered empty 31 5 17 23 22 0 total unanswered 31 5 17 23 22 0 c@1 measure 0.55 0.42 0.46 0.43 0.30 0.24
  • 9.  eLearning – fast answer for ~30% questions  Robotics – communication  CriES 2010 – identify experts on Yahoo! Answers
  • 10. Similar questions Answer Ok? Exista aplicatii in care folosirea Design Patterns-urilor sa nu fie eficienta? Evident (de exemplu un program Hello World)... Go La ce altceva design pattrenurile ar putea fi aplicate? Gasirea solutiei la o problema, crearea unui limbaj de programator avansat, in scrierea documentatiei, in discutii cu colegii de la o firma de software. Go Care este diferenta dintre pattern si o expresie (idiom) de codare. Nu am auzit de expresia idiom de codare, dar pare ceva particular, pe cand design pattern-ul este general... Go Care este diferenta dintre pattern si clase. Un design pattern este o solutie la o problema si prin urmare este compusa dintr-o ierarhie de clase intre care avem relatii. Go Este design pattern-ul diferit de pattern? De ce a fost ales acest nume? Design pattern-ul este un pattern in domeniul ingineriei software. Nu stiu de ce a fost ales acest nume.... :) Go Folosim Design Patterns in aceeasi aplicatie sau le folosim in aplicatii diferite? In aceeasi aplicatie. Go Ce este un design pattern? In primul rand: un nume, o problema si o solutie Go Questions Answer Priority Status Details La ce se folosesc design pattern-urile? normal nevoieN eaparat Go Raspunde la intrebare Raspuns Go Exception handlingul in Java poate fi considerat o aplicatie a Decorator pattern? urgent nevoieN eaparat Go Raspunde la intrebare Raspuns Go Exista aplicatii in care folosirea Design Patterns- urilor sa nu fie eficienta? Evident (de exemplu un program Hello World)... normal doarAsa La ce altceva design Gasirea solutiei la o problema, crearea unui limbaj de programator avansat, in saAfluM
  • 11.  With Swoogle we extend the knowledge base  The ontologies returned are then converted to AIML format and saved in the robot’s memory
  • 12. Initial digraph Initial Yahoo!answers collections en fr ge sp Eliminate stop words Domains keywords Initial users questions Eliminate stop words Questions keywords Relevant words for questions Relevant words for domains Similarity score between questions and domains Run 2 Run 1Run 0
  • 13.  UAIC QA system evolved over time (from 9 % in 2006 at 47.5 % in 2010)  The main problem is related to quality and quantity of Romanian resources involved  In present we are concerned with using of QA components in other applications in order to improve their capabilities

Notas do Editor

  1. Swoogle – a semantic web search engine