SlideShare una empresa de Scribd logo
1 de 44
Asking Clarifying Questions in
Open-Domain Information-
Seeking Conversations
Mohammad Aliannejadi(1), Hamed Zamani(2), Fabio Crestani(1), and W. Bruce Croft(2)
(1) Università della Svizzera italiana (USI), Switzerland
(2) University of Massachusetts Amherst, USA
© @dawnieando; @JeffD
5
6
7
8
Can we ask questions to clarify
the user information needs?
Johannes Kiesel et al. Toward Voice Query Clarification. SIGIR 2018
Radlinski and Craswell. A Theoretical Framework for Conversational Search. CHIIR 2017
How to evaluate?
ClueWeb Collection
• A part of the Lemur Project
• A common web crawl (English) with 50M documents
• TREC Web Track 2009 – 2012
• Ad-hoc retrieval and diversification tasks
TREC facets
An offline evaluation methodology
• We assume that each user is interested in one facet per topic.
An offline evaluation methodology
• Let be the set of topics (queries).
• A collection of facet sets:
• includes all defined facets for topic .
• A collection of clarifying question sets:
• With including all clarifying questions relevant to topic .
• An offline evaluation requires defining .
•
Borrowed from the ClueWeb Collection
Question Verification and Facet Linking
• Two main concerns:
• Precision: how is the quality of the collected clarifying questions?
• Recall: are all facets addressed by at least one clarifying question?
• Two expert annotators:
• Marked invalid and duplicate questions.
• Linked questions to the facets they found relevant.
• Facets with no questions: generated new questions relevant to them.
An offline evaluation methodology
• Let be the set of topics (queries).
• A collection of facet sets:
• includes all defined facets for topic .
• A collection of clarifying question sets:
• With including all clarifying questions relevant to topic .
• An offline evaluation requires defining .
•
Borrowed from the ClueWeb Collection
Quality Check
• Regular quality checks on the collected answers.
• Manual checks on 10% of submissions per worker.
• If any invalid answer was observed, we then checked all the submissions of the
corresponding worker.
• Invalid answers were removed and workers banned from future tasks.
• Disabled copy/paste feature.
• Monitored keystrokes.
Qulac: Questions for Lack of Clarity
Qulac has two meanings in Persian:
• blizzard
• wonderful or masterpiece
© HBO
Learning to ask clarifying
questions
Question
Retrieval
Question Retrieval
• Task: Given a topic and a context (question-answer history), retrieve
clarifying questions.
• Desired objective: high recall
• Approaches:
• Term matching retrieval models: language models, BM25, RM3 (query
expansion)
• Learning to rank: LambdaMART, RankNet, neural ranking models (e.g., BERT)
Question Retrieval
Question
Retrieval
Question Selection
• Task: selecting a clarifying question that leads to retrieval improvement
• Objective: high precision (in retrieval)
• Approaches:
• Query performance prediction (QPP): predicting the retrieval performance after asking each
question (without answer) and selecting the one with the highest QPP.
• Learning to rank: defining a set of features for ranking questions. The features include QPP,
similarity to the topic, similarity to the context, etc.
• Neural ranking models: learning to rank with representation learning (e.g., BERT)
Question Selection
Asking only one good question improves the performance by over 100%.
Case Study Negative answer; new information. Retrieval model fails.
Case Study Open question; new information.
Future Directions
• Utilizing positive and negative feedback for document retrieval.
• Joint modeling of question retrieval and selection.
• Question generation.
• Determining the number of questions to ask based on the system’s
confidence.
• Explore other ways of evaluating a system:
• Conversation turns;
• Retrieval performance.
Conclusions
• Asking clarifying questions in open-domain information-seeking conversations.
• Qulac: a collection for automatic offline evaluation of asking clarifying questions for
conversational IR.
• A simple yet effective retrieval framework.
• Asking only one good question improves the performance by over 100%!
• More improvement for:
• Shorter queries;
• Ambiguous queries.
Questions?
Qulac is publicly available at http://bit.ly/QulacData
Thanks to SIGIR for the student travel grant!

Más contenido relacionado

La actualidad más candente

Question Answering System using machine learning approach
Question Answering System using machine learning approachQuestion Answering System using machine learning approach
Question Answering System using machine learning approachGarima Nanda
 
FriendsQA: Open-domain Question Answering on TV Show Transcripts
FriendsQA: Open-domain Question Answering on TV Show TranscriptsFriendsQA: Open-domain Question Answering on TV Show Transcripts
FriendsQA: Open-domain Question Answering on TV Show TranscriptsJinho Choi
 
Empirical Evaluation of Active Learning in Recommender Systems
Empirical Evaluation of Active Learning in Recommender SystemsEmpirical Evaluation of Active Learning in Recommender Systems
Empirical Evaluation of Active Learning in Recommender SystemsUniversity of Bergen
 
Using GradeMark to improve feedback and involve students in the marking process
Using GradeMark to improve feedback and involve students in the marking processUsing GradeMark to improve feedback and involve students in the marking process
Using GradeMark to improve feedback and involve students in the marking processSara Marsham
 
User Personality and the New User Problem in a Context-Aware Point of Interes...
User Personality and the New User Problem in a Context-Aware Point of Interes...User Personality and the New User Problem in a Context-Aware Point of Interes...
User Personality and the New User Problem in a Context-Aware Point of Interes...University of Bergen
 
Using interactive models to enhance UML education
Using interactive models to enhance UML educationUsing interactive models to enhance UML education
Using interactive models to enhance UML educationStephen Frezza
 
Learning-Based Evaluation of Visual Analytic Systems.
Learning-Based Evaluation of Visual Analytic Systems.Learning-Based Evaluation of Visual Analytic Systems.
Learning-Based Evaluation of Visual Analytic Systems.BELIV Workshop
 
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...Pieter Heyvaert
 
Multiple Response Questions - Allowing for chance in authentic assessments
Multiple Response Questions - Allowing for chance in authentic assessmentsMultiple Response Questions - Allowing for chance in authentic assessments
Multiple Response Questions - Allowing for chance in authentic assessmentsMhairi Mcalpine
 
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...eMadrid network
 
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...Twitter Inc.
 
Survey Research In Empirical Software Engineering
Survey Research In Empirical Software EngineeringSurvey Research In Empirical Software Engineering
Survey Research In Empirical Software Engineeringalessio_ferrari
 
Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...Lifeng (Aaron) Han
 
Proposal Templet 10page
Proposal Templet 10pageProposal Templet 10page
Proposal Templet 10pageCho Li Hao
 
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...AI Chatbot Service Framework based on Backpropagation Network for Predicting ...
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...資彥 解
 
Data Collection and Analysis Tools
Data Collection and Analysis ToolsData Collection and Analysis Tools
Data Collection and Analysis ToolsCaren Gamboa
 
Developing high content image analysis software for biologists
Developing high content image analysis software for biologistsDeveloping high content image analysis software for biologists
Developing high content image analysis software for biologistsClaire McQuin
 

La actualidad más candente (20)

Question Answering System using machine learning approach
Question Answering System using machine learning approachQuestion Answering System using machine learning approach
Question Answering System using machine learning approach
 
FriendsQA: Open-domain Question Answering on TV Show Transcripts
FriendsQA: Open-domain Question Answering on TV Show TranscriptsFriendsQA: Open-domain Question Answering on TV Show Transcripts
FriendsQA: Open-domain Question Answering on TV Show Transcripts
 
2011 EASE - Motivation in Software Engineering: A Systematic Review Update
2011 EASE - Motivation in Software Engineering: A Systematic Review Update2011 EASE - Motivation in Software Engineering: A Systematic Review Update
2011 EASE - Motivation in Software Engineering: A Systematic Review Update
 
Literature review
Literature reviewLiterature review
Literature review
 
Empirical Evaluation of Active Learning in Recommender Systems
Empirical Evaluation of Active Learning in Recommender SystemsEmpirical Evaluation of Active Learning in Recommender Systems
Empirical Evaluation of Active Learning in Recommender Systems
 
Using GradeMark to improve feedback and involve students in the marking process
Using GradeMark to improve feedback and involve students in the marking processUsing GradeMark to improve feedback and involve students in the marking process
Using GradeMark to improve feedback and involve students in the marking process
 
User Personality and the New User Problem in a Context-Aware Point of Interes...
User Personality and the New User Problem in a Context-Aware Point of Interes...User Personality and the New User Problem in a Context-Aware Point of Interes...
User Personality and the New User Problem in a Context-Aware Point of Interes...
 
Using interactive models to enhance UML education
Using interactive models to enhance UML educationUsing interactive models to enhance UML education
Using interactive models to enhance UML education
 
Learning-Based Evaluation of Visual Analytic Systems.
Learning-Based Evaluation of Visual Analytic Systems.Learning-Based Evaluation of Visual Analytic Systems.
Learning-Based Evaluation of Visual Analytic Systems.
 
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...
Ontology-Based Data Access Mapping Generation using Data, Schema, Query, and ...
 
Introduction to Survey Data Quality
Introduction to Survey Data Quality  Introduction to Survey Data Quality
Introduction to Survey Data Quality
 
Multiple Response Questions - Allowing for chance in authentic assessments
Multiple Response Questions - Allowing for chance in authentic assessmentsMultiple Response Questions - Allowing for chance in authentic assessments
Multiple Response Questions - Allowing for chance in authentic assessments
 
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...
2022_03_28 EDUCON 2022 “Replication of an Evaluation of Teacher Training in t...
 
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...
Towards Privacy-Preserving Evaluation for Information Retrieval Models over I...
 
Survey Research In Empirical Software Engineering
Survey Research In Empirical Software EngineeringSurvey Research In Empirical Software Engineering
Survey Research In Empirical Software Engineering
 
Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...
 
Proposal Templet 10page
Proposal Templet 10pageProposal Templet 10page
Proposal Templet 10page
 
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...AI Chatbot Service Framework based on Backpropagation Network for Predicting ...
AI Chatbot Service Framework based on Backpropagation Network for Predicting ...
 
Data Collection and Analysis Tools
Data Collection and Analysis ToolsData Collection and Analysis Tools
Data Collection and Analysis Tools
 
Developing high content image analysis software for biologists
Developing high content image analysis software for biologistsDeveloping high content image analysis software for biologists
Developing high content image analysis software for biologists
 

Similar a Asking Clarifying Questions in Open-Domain Information-Seeking Conversations

Improving neural question generation using answer separation
Improving neural question generation using answer separationImproving neural question generation using answer separation
Improving neural question generation using answer separationNAVER Engineering
 
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Lucidworks
 
Evaluating Semantic Search Systems to Identify Future Directions of Research
Evaluating Semantic Search Systems to Identify Future Directions of ResearchEvaluating Semantic Search Systems to Identify Future Directions of Research
Evaluating Semantic Search Systems to Identify Future Directions of ResearchStuart Wrigley
 
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...Lucidworks
 
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningLucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningJoaquin Delgado PhD.
 
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningLucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningS. Diana Hu
 
Dice.com Bay Area Search - Beyond Learning to Rank Talk
Dice.com Bay Area Search - Beyond Learning to Rank TalkDice.com Bay Area Search - Beyond Learning to Rank Talk
Dice.com Bay Area Search - Beyond Learning to Rank TalkSimon Hughes
 
Addictive links, Keynote talk at WWW 2014 workshop
Addictive links, Keynote talk at WWW 2014 workshopAddictive links, Keynote talk at WWW 2014 workshop
Addictive links, Keynote talk at WWW 2014 workshopPeter Brusilovsky
 
Multi-method Evaluation in Scientific Paper Recommender Systems
Multi-method Evaluation in Scientific Paper Recommender SystemsMulti-method Evaluation in Scientific Paper Recommender Systems
Multi-method Evaluation in Scientific Paper Recommender SystemsAravind Sesagiri Raamkumar
 
Multimedia Answer Generation for Community Question Answering
Multimedia Answer Generation for Community Question AnsweringMultimedia Answer Generation for Community Question Answering
Multimedia Answer Generation for Community Question AnsweringSWAMI06
 
empirical-SLR.pptx
empirical-SLR.pptxempirical-SLR.pptx
empirical-SLR.pptxJitha Kannan
 
Deep Learning Models for Question Answering
Deep Learning Models for Question AnsweringDeep Learning Models for Question Answering
Deep Learning Models for Question AnsweringSujit Pal
 
SEMAT & SE Education - LACREST 2013 Keynote
SEMAT & SE Education - LACREST 2013 KeynoteSEMAT & SE Education - LACREST 2013 Keynote
SEMAT & SE Education - LACREST 2013 Keynoteperaire
 
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...Joaquin Delgado PhD.
 
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning... RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...S. Diana Hu
 
Combining IR with Relevance Feedback for Concept Location
Combining IR with Relevance Feedback for Concept LocationCombining IR with Relevance Feedback for Concept Location
Combining IR with Relevance Feedback for Concept LocationSonia Haiduc
 
Influence of Timeline and Named-entity Components on User Engagement
Influence of Timeline and Named-entity Components on User Engagement Influence of Timeline and Named-entity Components on User Engagement
Influence of Timeline and Named-entity Components on User Engagement Roi Blanco
 
Survey Research Methods with Lynn Silipigni Connaway
Survey Research Methods with Lynn Silipigni ConnawaySurvey Research Methods with Lynn Silipigni Connaway
Survey Research Methods with Lynn Silipigni ConnawayLynn Connaway
 

Similar a Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (20)

Improving neural question generation using answer separation
Improving neural question generation using answer separationImproving neural question generation using answer separation
Improving neural question generation using answer separation
 
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
 
Evaluating Semantic Search Systems to Identify Future Directions of Research
Evaluating Semantic Search Systems to Identify Future Directions of ResearchEvaluating Semantic Search Systems to Identify Future Directions of Research
Evaluating Semantic Search Systems to Identify Future Directions of Research
 
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...
Where Search Meets Machine Learning: Presented by Diana Hu & Joaquin Delgado,...
 
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningLucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
 
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine LearningLucene/Solr Revolution 2015: Where Search Meets Machine Learning
Lucene/Solr Revolution 2015: Where Search Meets Machine Learning
 
Dice.com Bay Area Search - Beyond Learning to Rank Talk
Dice.com Bay Area Search - Beyond Learning to Rank TalkDice.com Bay Area Search - Beyond Learning to Rank Talk
Dice.com Bay Area Search - Beyond Learning to Rank Talk
 
Addictive links, Keynote talk at WWW 2014 workshop
Addictive links, Keynote talk at WWW 2014 workshopAddictive links, Keynote talk at WWW 2014 workshop
Addictive links, Keynote talk at WWW 2014 workshop
 
lecture1.pdf
lecture1.pdflecture1.pdf
lecture1.pdf
 
Multi-method Evaluation in Scientific Paper Recommender Systems
Multi-method Evaluation in Scientific Paper Recommender SystemsMulti-method Evaluation in Scientific Paper Recommender Systems
Multi-method Evaluation in Scientific Paper Recommender Systems
 
Multimedia Answer Generation for Community Question Answering
Multimedia Answer Generation for Community Question AnsweringMultimedia Answer Generation for Community Question Answering
Multimedia Answer Generation for Community Question Answering
 
empirical-SLR.pptx
empirical-SLR.pptxempirical-SLR.pptx
empirical-SLR.pptx
 
Deep Learning Models for Question Answering
Deep Learning Models for Question AnsweringDeep Learning Models for Question Answering
Deep Learning Models for Question Answering
 
Addictive links: Adaptive Navigation Support in College-Level Courses
Addictive links: Adaptive Navigation Support in College-Level CoursesAddictive links: Adaptive Navigation Support in College-Level Courses
Addictive links: Adaptive Navigation Support in College-Level Courses
 
SEMAT & SE Education - LACREST 2013 Keynote
SEMAT & SE Education - LACREST 2013 KeynoteSEMAT & SE Education - LACREST 2013 Keynote
SEMAT & SE Education - LACREST 2013 Keynote
 
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
 
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning... RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 
Combining IR with Relevance Feedback for Concept Location
Combining IR with Relevance Feedback for Concept LocationCombining IR with Relevance Feedback for Concept Location
Combining IR with Relevance Feedback for Concept Location
 
Influence of Timeline and Named-entity Components on User Engagement
Influence of Timeline and Named-entity Components on User Engagement Influence of Timeline and Named-entity Components on User Engagement
Influence of Timeline and Named-entity Components on User Engagement
 
Survey Research Methods with Lynn Silipigni Connaway
Survey Research Methods with Lynn Silipigni ConnawaySurvey Research Methods with Lynn Silipigni Connaway
Survey Research Methods with Lynn Silipigni Connaway
 

Último

Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024eCommerce Institute
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxraffaeleoman
 
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfCTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfhenrik385807
 
If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaKayode Fayemi
 
Presentation on Engagement in Book Clubs
Presentation on Engagement in Book ClubsPresentation on Engagement in Book Clubs
Presentation on Engagement in Book Clubssamaasim06
 
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )Pooja Nehwal
 
Mathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMoumonDas2
 
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceDelhi Call girls
 
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...henrik385807
 
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, YardstickSaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, Yardsticksaastr
 
ANCHORING SCRIPT FOR A CULTURAL EVENT.docx
ANCHORING SCRIPT FOR A CULTURAL EVENT.docxANCHORING SCRIPT FOR A CULTURAL EVENT.docx
ANCHORING SCRIPT FOR A CULTURAL EVENT.docxNikitaBankoti2
 
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night Enjoy
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night EnjoyCall Girl Number in Khar Mumbai📲 9892124323 💞 Full Night Enjoy
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night EnjoyPooja Nehwal
 
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Pooja Nehwal
 
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Kayode Fayemi
 
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxMohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxmohammadalnahdi22
 
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Hasting Chen
 
Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)Chameera Dedduwage
 
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Delhi Call girls
 
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesVVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesPooja Nehwal
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...Sheetaleventcompany
 

Último (20)

Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
Andrés Ramírez Gossler, Facundo Schinnea - eCommerce Day Chile 2024
 
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptxChiulli_Aurora_Oman_Raffaele_Beowulf.pptx
Chiulli_Aurora_Oman_Raffaele_Beowulf.pptx
 
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdfCTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
CTAC 2024 Valencia - Henrik Hanke - Reduce to the max - slideshare.pdf
 
If this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New NigeriaIf this Giant Must Walk: A Manifesto for a New Nigeria
If this Giant Must Walk: A Manifesto for a New Nigeria
 
Presentation on Engagement in Book Clubs
Presentation on Engagement in Book ClubsPresentation on Engagement in Book Clubs
Presentation on Engagement in Book Clubs
 
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
WhatsApp 📞 9892124323 ✅Call Girls In Juhu ( Mumbai )
 
Mathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptxMathematics of Finance Presentation.pptx
Mathematics of Finance Presentation.pptx
 
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 93 Noida Escorts >༒8448380779 Escort Service
 
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
CTAC 2024 Valencia - Sven Zoelle - Most Crucial Invest to Digitalisation_slid...
 
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, YardstickSaaStr Workshop Wednesday w/ Lucas Price, Yardstick
SaaStr Workshop Wednesday w/ Lucas Price, Yardstick
 
ANCHORING SCRIPT FOR A CULTURAL EVENT.docx
ANCHORING SCRIPT FOR A CULTURAL EVENT.docxANCHORING SCRIPT FOR A CULTURAL EVENT.docx
ANCHORING SCRIPT FOR A CULTURAL EVENT.docx
 
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night Enjoy
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night EnjoyCall Girl Number in Khar Mumbai📲 9892124323 💞 Full Night Enjoy
Call Girl Number in Khar Mumbai📲 9892124323 💞 Full Night Enjoy
 
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
Navi Mumbai Call Girls Service Pooja 9892124323 Real Russian Girls Looking Mo...
 
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
Governance and Nation-Building in Nigeria: Some Reflections on Options for Po...
 
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptxMohammad_Alnahdi_Oral_Presentation_Assignment.pptx
Mohammad_Alnahdi_Oral_Presentation_Assignment.pptx
 
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
Re-membering the Bard: Revisiting The Compleat Wrks of Wllm Shkspr (Abridged)...
 
Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)Introduction to Prompt Engineering (Focusing on ChatGPT)
Introduction to Prompt Engineering (Focusing on ChatGPT)
 
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
Night 7k Call Girls Noida Sector 128 Call Me: 8448380779
 
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara ServicesVVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
VVIP Call Girls Nalasopara : 9892124323, Call Girls in Nalasopara Services
 
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
No Advance 8868886958 Chandigarh Call Girls , Indian Call Girls For Full Nigh...
 

Asking Clarifying Questions in Open-Domain Information-Seeking Conversations

  • 1. Asking Clarifying Questions in Open-Domain Information- Seeking Conversations Mohammad Aliannejadi(1), Hamed Zamani(2), Fabio Crestani(1), and W. Bruce Croft(2) (1) Università della Svizzera italiana (USI), Switzerland (2) University of Massachusetts Amherst, USA
  • 3.
  • 4.
  • 5. 5
  • 6. 6
  • 7. 7
  • 8. 8
  • 9.
  • 10.
  • 11.
  • 12. Can we ask questions to clarify the user information needs? Johannes Kiesel et al. Toward Voice Query Clarification. SIGIR 2018 Radlinski and Craswell. A Theoretical Framework for Conversational Search. CHIIR 2017
  • 13.
  • 14.
  • 16. ClueWeb Collection • A part of the Lemur Project • A common web crawl (English) with 50M documents • TREC Web Track 2009 – 2012 • Ad-hoc retrieval and diversification tasks
  • 18. An offline evaluation methodology • We assume that each user is interested in one facet per topic.
  • 19. An offline evaluation methodology • Let be the set of topics (queries). • A collection of facet sets: • includes all defined facets for topic . • A collection of clarifying question sets: • With including all clarifying questions relevant to topic . • An offline evaluation requires defining . • Borrowed from the ClueWeb Collection
  • 20.
  • 21.
  • 22.
  • 23. Question Verification and Facet Linking • Two main concerns: • Precision: how is the quality of the collected clarifying questions? • Recall: are all facets addressed by at least one clarifying question? • Two expert annotators: • Marked invalid and duplicate questions. • Linked questions to the facets they found relevant. • Facets with no questions: generated new questions relevant to them.
  • 24.
  • 25. An offline evaluation methodology • Let be the set of topics (queries). • A collection of facet sets: • includes all defined facets for topic . • A collection of clarifying question sets: • With including all clarifying questions relevant to topic . • An offline evaluation requires defining . • Borrowed from the ClueWeb Collection
  • 26.
  • 27. Quality Check • Regular quality checks on the collected answers. • Manual checks on 10% of submissions per worker. • If any invalid answer was observed, we then checked all the submissions of the corresponding worker. • Invalid answers were removed and workers banned from future tasks. • Disabled copy/paste feature. • Monitored keystrokes.
  • 28. Qulac: Questions for Lack of Clarity Qulac has two meanings in Persian: • blizzard • wonderful or masterpiece © HBO
  • 29. Learning to ask clarifying questions
  • 31. Question Retrieval • Task: Given a topic and a context (question-answer history), retrieve clarifying questions. • Desired objective: high recall • Approaches: • Term matching retrieval models: language models, BM25, RM3 (query expansion) • Learning to rank: LambdaMART, RankNet, neural ranking models (e.g., BERT)
  • 34. Question Selection • Task: selecting a clarifying question that leads to retrieval improvement • Objective: high precision (in retrieval) • Approaches: • Query performance prediction (QPP): predicting the retrieval performance after asking each question (without answer) and selecting the one with the highest QPP. • Learning to rank: defining a set of features for ranking questions. The features include QPP, similarity to the topic, similarity to the context, etc. • Neural ranking models: learning to rank with representation learning (e.g., BERT)
  • 35. Question Selection Asking only one good question improves the performance by over 100%.
  • 36.
  • 37.
  • 38.
  • 39.
  • 40. Case Study Negative answer; new information. Retrieval model fails.
  • 41. Case Study Open question; new information.
  • 42. Future Directions • Utilizing positive and negative feedback for document retrieval. • Joint modeling of question retrieval and selection. • Question generation. • Determining the number of questions to ask based on the system’s confidence. • Explore other ways of evaluating a system: • Conversation turns; • Retrieval performance.
  • 43. Conclusions • Asking clarifying questions in open-domain information-seeking conversations. • Qulac: a collection for automatic offline evaluation of asking clarifying questions for conversational IR. • A simple yet effective retrieval framework. • Asking only one good question improves the performance by over 100%! • More improvement for: • Shorter queries; • Ambiguous queries.
  • 44. Questions? Qulac is publicly available at http://bit.ly/QulacData Thanks to SIGIR for the student travel grant!

Notas del editor

  1. <number>
  2. make a frame of slides with logos... <number>
  3. make it more dialogue <number>
  4. put confidence here in the image <number>
  5. change this <number>
  6. remove one or two <number>
  7. more stress on confidence merge with future directions <number>