1 Just-in-Time Interactive Question Answering Language Computer Corporation Sanda Harabagiu, PI John Lehmann John Williams Paul Aarseth.

Slides:



Advertisements
Similar presentations
1 Evaluation Rong Jin. 2 Evaluation  Evaluation is key to building effective and efficient search engines usually carried out in controlled experiments.
Advertisements

Developing and Evaluating a Query Recommendation Feature to Assist Users with Online Information Seeking & Retrieval With graduate students: Karl Gyllstrom,
Overview of Collaborative Information Retrieval (CIR) at FIRE 2012 Debasis Ganguly, Johannes Leveling, Gareth Jones School of Computing, CNGL, Dublin City.
Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
Language Model based Information Retrieval: University of Saarland 1 A Hidden Markov Model Information Retrieval System Mahboob Alam Khalid.
1 Oct 30, 2006 LogicSQL-based Enterprise Archive and Search System How to organize the information and make it accessible and useful ? Li-Yan Yuan.
Evaluating Search Engine
The Role of Software Engineering Brief overview of relationship of SE to managing DSD risks 1.
Modern Information Retrieval
Chapter 8 The Information Systems Planning Process Meeting the Challenges of Information Systems Planning Charles Cohen Presented by: Pablo De Luca.
The Informative Role of WordNet in Open-Domain Question Answering Marius Paşca and Sanda M. Harabagiu (NAACL 2001) Presented by Shauna Eggers CS 620 February.
INFO 624 Week 3 Retrieval System Evaluation
Retrieval Evaluation. Brief Review Evaluation of implementations in computer science often is in terms of time and space complexity. With large document.
An investigation of query expansion terms Gheorghe Muresan Rutgers University, School of Communication, Information and Library Science 4 Huntington St.,
Latent Semantic Analysis (LSA). Introduction to LSA Learning Model Uses Singular Value Decomposition (SVD) to simulate human learning of word and passage.
ISP 433/633 Week 6 IR Evaluation. Why Evaluate? Determine if the system is desirable Make comparative assessments.
WISER: Newspapers online : an introduction to the scope and range of recent and current newspapers available on Oxlip, including hints on effective search.
Employing Two Question Answering Systems in TREC 2005 Harabagiu, Moldovan, et al 2005 Language Computer Corporation.
Overview of Search Engines
Orientation to the Social Studies K to 7 Integrated Resource Package 2006.
Substantive Conversations in the Classroom.
Microsoft Access 2007 Microsoft Access 2007 Introduction to Database Programs.
COURSE OVERVIEW COURSE REQUIREMENTS KNOWLEDGE AND SKILLS STUDENT EXPECTATIONS Global Business.
Search and Retrieval: Relevance and Evaluation Prof. Marti Hearst SIMS 202, Lecture 20.
Selecting Researchable Topics and Questions
On Roles of Models in Information Systems (Arne Sølvberg) Gustavo Carvalho 26 de Agosto de 2010.
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
AQUAINT PI meeting Dec. 3-6, 2002 AQUAINT Dialogue Experiment Jean Scholtz Information Access Division National Institute of Standards and Technology
1. An Overview of the Data Analysis and Probability Standard for School Mathematics? 2.
IBM’s Watson. IBM’s Watson represents an innovation in Data Analysis Computing called Deep QA (Question Answering) Their project is a hybrid technology.
1 The BT Digital Library A case study in intelligent content management Paul Warren
Author: William Tunstall-Pedoe Presenter: Bahareh Sarrafzadeh CS 886 Spring 2015.
AnswerBus Question Answering System Zhiping Zheng School of Information, University of Michigan HLT 2002.
Aware Discovering characteristics of habitable question answering systems with iterative formative evaluation Bill Ogden Ron Zacharski New Mexico State.
Copyright © 2014 Wolters Kluwer Health | Lippincott Williams & Wilkins Nursing Issues: A Call to Political Action Chapter 1.
Ch 1-1 © 2004 Pearson Education, Inc. Pearson Prentice Hall, Pearson Education, Upper Saddle River, NJ Ostwald and McLaren / Cost Analysis and Estimating.
21/11/2002 The Integration of Lexical Knowledge and External Resources for QA Hui YANG, Tat-Seng Chua Pris, School of Computing.
©2003 Paula Matuszek CSC 9010: Text Mining Applications Document Summarization Dr. Paula Matuszek (610)
1 Boostrapping language models for dialogue systems Karl Weilhammer, Matthew N Stuttle, Steve Young Presenter: Hsuan-Sheng Chiu.
Collocations and Information Management Applications Gregor Erbach Saarland University Saarbrücken.
From Question-Answering to Information-Seeking Dialogs Jerry R. Hobbs Artificial Intelligence Center SRI International Menlo Park, California (with Douglas.
WIRED Week 3 Syllabus Update (next week) Readings Overview - Quick Review of Last Week’s IR Models (if time) - Evaluating IR Systems - Understanding Queries.
The Structure of Information Retrieval Systems LBSC 708A/CMSC 838L Douglas W. Oard and Philip Resnik Session 1: September 4, 2001.
AQUAINT Kickoff Meeting Advanced Techniques for Answer Extraction and Formulation Language Computer Corporation Dallas, Texas.
Splitting Complex Temporal Questions for Question Answering systems ACL 2004.
Next Generation Search Engines Ehsun Daroodi 1 Feb, 2003.
Educational Research: Competencies for Analysis and Application, 9 th edition. Gay, Mills, & Airasian © 2009 Pearson Education, Inc. All rights reserved.
Chapter 8 Evaluating Search Engine. Evaluation n Evaluation is key to building effective and efficient search engines  Measurement usually carried out.
Endangered Species A Collaborative Teaching Unit.
United Nations Economic Commission for Europe Statistical Division Data Initiatives: The UNECE Gender Database and Website Victoria Velkoff On behalf of.
AQUAINT June 2002 Workshop June 2002 Just-in-Time Interactive Question Answering Sanda Harabagiu: PI Language Computer Corporation.
HITIQA: Scenario Based Question Answering Tomek Strzalkowski, et al The State University of New York at Albany Paul Kantor, et al Rutgers University Boris.
A Classification-based Approach to Question Answering in Discussion Boards Liangjie Hong, Brian D. Davison Lehigh University (SIGIR ’ 09) Speaker: Cho,
1 Workplace Emotions, Values, and Ethics. 2 Agenda Collect team research questions and subtopics Review case study requirements Discuss emotions, then.
公司 標誌 Question Answering System Introduction to Q-A System 資訊四 B 張弘霖 資訊四 B 王惟正.
Building Bridges: Embedding outcome evaluation in national and state TA delivery Ella Taylor Diane Haynes John Killoran Sarah Beaird August 1, 2006.
Query Suggestions in the Absence of Query Logs Sumit Bhatia, Debapriyo Majumdar,Prasenjit Mitra SIGIR’11, July 24–28, 2011, Beijing, China.
Topic by Topic Performance of Information Retrieval Systems Walter Liggett National Institute of Standards and Technology TREC-7 (1999)
Chapter. 3: Retrieval Evaluation 1/2/2016Dr. Almetwally Mostafa 1.
Prepared By: Razif Razali 1 TMK 264: COMPUTER SECURITY CHAPTER SIX : ADMINISTERING SECURITY.
Strategies for Advanced Question Answering Sanda Harabagiu & Finley Lacatusu Language Computer Corporation HLT-NAACL2004 Workshop.
AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
1. 2 Engineering Economics (2+0) Fundamentals of Engineering Economics-2 And Time value of Money Instructor: Prof. Dr. Attaullah Shah Lecture # 2 Department.
CONDUCTING RESEARCH – Lecture 19 Research- Where to Begin? What kind of information do you need? – Facts – Opinions – News reports – Research studies.
Using Blog Properties to Improve Retrieval Gilad Mishne (ICWSM 2007)
Information Storage and Retrieval Fall Lecture 1: Introduction and History.
INTER-AMERICAN DEVELOPMENT BANK CAPACITY BUILDING AND TRAINING.
Guangbing Yang Presentation for Xerox Docushare Symposium in 2011
Using Access to Implement a Relational Database
Analyzing and Organizing Information
Presentation transcript:

1 Just-in-Time Interactive Question Answering Language Computer Corporation Sanda Harabagiu, PI John Lehmann John Williams Paul Aarseth

2 Overview Project Introduction Preparation for “Wizard of Oz” pilot Performance in WOZ pilot Challenges encountered in WOZ pilot Current work and future plans

3 Research Project Objective Address the interactive aspect of QA systems by designing and implementing a dialog shell that can be used with any QA system

4 Tasks in JITIQA

5 Predicted Challenges in WOZ We imagined the following about the assessor Asks complex questions, compared to TREC Sample showed < 1/3 with “known” answer types Wants fast responses Assumes dialogue context (pronouns, ellipses) Has no knowledge of question formulation Assumes the QA system’s collection contains answer

6 Preparation for WOZ Extend work in factual QA with two approaches Information/knowledge-centric Create a Question/Answer Database (QADB) Develop a question similarity metric Build higher quality domain-specific document collections User-centric Reformulate questions to resolve references and incorporate context Decompose complex questions into simpler ones

7 Question/Answer Database Because domain is closed, we may be able to predict questions and collect answers How well can we cover the range of possible questions? Process: 1. Split up topics between developers 2. Generate question and answer records 3. Rotate topics among developers

8 QADB Population For 10 domains, collected 334 question records, each with answers from multiple sources Perform retrieval of answers by computing question similarity based on concepts 33Surgery 37Sanchez 27Microsoft 33Japan 17Ivory Coast 57Indonesia 40Colombia 31Black Sea 35Africa 24Afghanistan #recsDomain

9 Question Concepts Q: “Why does so much opium production take place in Afghanistan?” Concept 1: cause Concept 2: popularity Concept 3: produced Other questions satisfying 100% of the concepts Why is so much opium produced in Afghanistan? Why is poppy farming popular in Afghanistan? For what reasons is growing poppy common in Afghanistan? What causes poppy farming to be so popular in Afghanistan? What makes opium farms so commonplace in Afghanistan?

10 Document Collection Reasons for document collection Alternative to slow Internet searches Pre-filtering documents for domain relevance Internet information is of low quality Keeps experiment repeatable

11 Documents Collected DomainNewsWeb Opium/Afghanistan1,7962,306 AIDS/Africa10,3957,189 Black Sea Pollution1,8674,131 FARC/Colombia4,0805,161 Indonesian Economy16,66514,704 Cell Phones/Ivory Coast1,2643,164 Joint Ventures/Japan1,9443,556 Microsoft/Viruses3,5077,553 Elizardo Sánchez Robotic Surgery5,4484,908 News source collections Documents from major newspapers with dates Collected with one general query per domain to catch all possibly relevant documents Used in pilot Web source collections Generally poor quality documents Multiple specific queries used per domain, saving top 500 documents each time Not used in pilot

12 Performance in Pilot Performance Measure P1P2 Final Answer65.7 Time Dialog Clarifications76 System Clarity Overall Assessors in pilots 1 and 2 graded our dialog based on several performance measures for each domain Scale: 1-7 with 7 representing “completely satisfied”

13 QADB Performance 945Robotic Surgery Total 615Elizardo Sánchez 413Microsoft/Viruses 642Joint Ventures/Japan 11263Cell Phones/Ivory Coast 13238Indonesian Economy 532FARC/Colombia 725Black Sea Pollution 8323AIDS/Africa 6123Opium/Afghanistan TotalNonePartFullDomain Number of questions QADB answered fully, partially, or not at all, for both pilot experiments combined

14 Complex Questions Complex questions require mapping into simpler questions “Biographical information needed on Elizardo Sanchez, Cuban dissident” When and where was Elizardo Sanchez born? Where did Elizardo Sanchez go to school? Who is in Elizardo Sanchez’s family? “Give some information on uses of robotic surgery in US and foreign countries?” What kinds of surgeries do robots perform? What laws govern robotic surgery in the US? What are the benefits of robotic surgery?

15 Complex Answer Types System only recognizes simple answer types Money - How much money can be made from opium smuggling? Locations - What countries are involved in fighting Afghan opium production? Date - When did opium production begin in Afghanistan? Most questions sought complex answers Cause – Why does so much opium production take place in Afghanistan? Action – What is being done to fight opium production? Effects – How have recent events affected opium production? Problems – What problems do counter narcotics face in Afghanistan? Policy – What is the United States’ financial commitment to drug control efforts?

16 Other Challenging Questions Ambiguous questions “During the years what was Indonesia’s currency exchange rate?” What measure is desired? An average? Each year? Follow-up questions A: “Kim currently works three days a week at WIN-TECH, a three-company joint venture...” Q: “who is kim?” Misleading questions Misspellings, slang, capitalization, statements

17 Current Work Automatic complex question break- down Specification of general terms “What elements cause Black Sea pollution?” Expand elements into companies, countries, chemicals Decomposition into members “What about Sherron Watkins’ family?” Decompose family into parents, children, spouse Dialog context understanding Coreference of anaphors

18 Future Plans Enhanced transformations of complex questions into simple ones Enhanced incorporation of context Ellipsis resolution Recognition of intensions Automatic and interactive generation of topic knowledge and QADB population