Semantic Retrieval for Question Answering Student Research Symposium Language Technologies Institute Matthew W. Bilotti September 23,

Slides:



Advertisements
Similar presentations
ThemeInformation Extraction for World Wide Web PaperUnsupervised Learning of Soft Patterns for Generating Definitions from Online News Author Cui, H.,
Advertisements

1 Evaluation Rong Jin. 2 Evaluation  Evaluation is key to building effective and efficient search engines usually carried out in controlled experiments.
QA-LaSIE Components The question document and each candidate answer document pass through all nine components of the QA-LaSIE system in the order shown.
NYU ANLP-00 1 Automatic Discovery of Scenario-Level Patterns for Information Extraction Roman Yangarber Ralph Grishman Pasi Tapanainen Silja Huttunen.
1 Question Answering in Biomedicine Student: Andreea Tutos Id: Supervisor: Diego Molla.
Information Retrieval in Practice
Question-Answering: Overview Ling573 Systems & Applications March 31, 2011.
T.Sharon - A.Frank 1 Internet Resources Discovery (IRD) Classic Information Retrieval (IR)
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.
Basi di dati distribuite Prof. M.T. PAZIENZA a.a
Web Logs and Question Answering Richard Sutcliffe 1, Udo Kruschwitz 2, Thomas Mandl University of Limerick, Ireland 2 - University of Essex, UK 3.
Advance Information Retrieval Topics Hassan Bashiri.
ITCS 6010 Natural Language Understanding. Natural Language Processing What is it? Studies the problems inherent in the processing and manipulation of.
1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
Employing Two Question Answering Systems in TREC 2005 Harabagiu, Moldovan, et al 2005 Language Computer Corporation.
Overview of Search Engines
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Information Retrieval in Practice
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
JAVELIN Project Briefing 1 AQUAINT Year I Mid-Year Review Language Technologies Institute Carnegie Mellon University Status Update for Mid-Year Program.
Challenges in Information Retrieval and Language Modeling Michael Shepherd Dalhousie University Halifax, NS Canada.
CSC 9010 Spring Paula Matuszek A Brief Overview of Watson.
Probabilistic Model for Definitional Question Answering Kyoung-Soo Han, Young-In Song, and Hae-Chang Rim Korea University SIGIR 2006.
Hang Cui et al. NUS at TREC-13 QA Main Task 1/20 National University of Singapore at the TREC- 13 Question Answering Main Task Hang Cui Keya Li Renxu Sun.
Reyyan Yeniterzi Weakly-Supervised Discovery of Named Entities Using Web Search Queries Marius Pasca Google CIKM 2007.
©2008 Srikanth Kallurkar, Quantum Leap Innovations, Inc. All rights reserved. Apollo – Automated Content Management System Srikanth Kallurkar Quantum Leap.
Semantic Search via XML Fragments: A High-Precision Approach to IR Jennifer Chu-Carroll, John Prager, David Ferrucci, and Pablo Duboue IBM T.J. Watson.
AnswerBus Question Answering System Zhiping Zheng School of Information, University of Michigan HLT 2002.
Question Answering.  Goal  Automatically answer questions submitted by humans in a natural language form  Approaches  Rely on techniques from diverse.
A Markov Random Field Model for Term Dependencies Donald Metzler W. Bruce Croft Present by Chia-Hao Lee.
Question Answering From Zero to Hero Elena Eneva 11 Oct 2001 Advanced IR Seminar.
Querying Structured Text in an XML Database By Xuemei Luo.
A Probabilistic Graphical Model for Joint Answer Ranking in Question Answering Jeongwoo Ko, Luo Si, Eric Nyberg (SIGIR ’ 07) Speaker: Cho, Chin Wei Advisor:
Abstract Question answering is an important task of natural language processing. Unification-based grammars have emerged as formalisms for reasoning about.
Carnegie Mellon School of Computer Science Copyright © 2001, Carnegie Mellon. All Rights Reserved. JAVELIN Project Briefing 1 AQUAINT Phase I Kickoff December.
Natural Language Based Reformulation Resource and Web Exploitation for Question Answering Ulf Hermjakob, Abdessamad Echihabi, Daniel Marcu University of.
A Language Independent Method for Question Classification COLING 2004.
21/11/2002 The Integration of Lexical Knowledge and External Resources for QA Hui YANG, Tat-Seng Chua Pris, School of Computing.
AQUAINT 18-Month Workshop 1 Light Semantic Processing for QA Language Technologies Institute, Carnegie Mellon B. Van Durme, Y. Huang, A. Kupsc and E. Nyberg.
Collocations and Information Management Applications Gregor Erbach Saarland University Saarbrücken.
LANGUAGE MODELS FOR RELEVANCE FEEDBACK Lee Won Hee.
Google’s Deep-Web Crawl By Jayant Madhavan, David Ko, Lucja Kot, Vignesh Ganapathy, Alex Rasmussen, and Alon Halevy August 30, 2008 Speaker : Sahana Chiwane.
EXPLOITING DYNAMIC VALIDATION FOR DOCUMENT LAYOUT CLASSIFICATION DURING METADATA EXTRACTION Kurt Maly Steven Zeil Mohammad Zubair WWW/Internet 2007 Vila.
Splitting Complex Temporal Questions for Question Answering systems ACL 2004.
JAVELIN Project Briefing AQUAINT Program 1 AQUAINT Workshop, October 2005 JAVELIN Project Briefing Eric Nyberg, Teruko Mitamura, Jamie Callan, Robert Frederking,
1/21 Automatic Discovery of Intentions in Text and its Application to Question Answering (ACL 2005 Student Research Workshop )
Department of Software and Computing Systems Research Group of Language Processing and Information Systems The DLSIUAES Team’s Participation in the TAC.
Probabilistic Latent Query Analysis for Combining Multiple Retrieval Sources Rong Yan Alexander G. Hauptmann School of Computer Science Carnegie Mellon.
Using a Named Entity Tagger to Generalise Surface Matching Text Patterns for Question Answering Mark A. Greenwood and Robert Gaizauskas Natural Language.
August 17, 2005Question Answering Passage Retrieval Using Dependency Parsing 1/28 Question Answering Passage Retrieval Using Dependency Parsing Hang Cui.
Automatic Question Answering  Introduction  Factoid Based Question Answering.
Comparing Document Segmentation for Passage Retrieval in Question Answering Jorg Tiedemann University of Groningen presented by: Moy’awiah Al-Shannaq
Mining Dependency Relations for Query Expansion in Passage Retrieval Renxu Sun, Chai-Huat Ong, Tat-Seng Chua National University of Singapore SIGIR2006.
Evidence from Content INST 734 Module 2 Doug Oard.
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
Relevance Models and Answer Granularity for Question Answering W. Bruce Croft and James Allan CIIR University of Massachusetts, Amherst.
DISTRIBUTED INFORMATION RETRIEVAL Lee Won Hee.
Keyword Translation Accuracy and Cross-Lingual Question Answering in Chinese and Japanese Teruko Mitamura Mengqiu Wang Hideki Shima Frank Lin In CMU EACL.
1 Question Answering and Logistics. 2 Class Logistics  Comments on proposals will be returned next week and may be available as early as Monday  Look.
Text Information Management ChengXiang Zhai, Tao Tao, Xuehua Shen, Hui Fang, Azadeh Shakery, Jing Jiang.
Feature Assignment LBSC 878 February 22, 1999 Douglas W. Oard and Dagobert Soergel.
Question Answering Passage Retrieval Using Dependency Relations (SIGIR 2005) (National University of Singapore) Hang Cui, Renxu Sun, Keya Li, Min-Yen Kan,
Information Retrieval in Practice
Designing Cross-Language Information Retrieval System using various Techniques of Query Expansion and Indexing for Improved Performance  Hello everyone,
Search Engine Architecture
Traditional Question Answering System: an Overview
INFORMATION RETRIEVAL TECHNIQUES BY DR. ADNAN ABID
CS246: Information Retrieval
Information Retrieval and Web Design
Presentation transcript:

Semantic Retrieval for Question Answering Student Research Symposium Language Technologies Institute Matthew W. Bilotti September 23, 2005

Outline What is Question Answering? What is the cause of wrong answers? What is Semantic Retrieval, and can it help? What have other teams tried? How is JAVELIN using Semantic Retrieval? How can we evaluate the impact of Semantic Retrieval on Question Answering systems? Where can we go from here?

What is Question Answering? A process that finds succinct answers to questions phrased in natural language Q: “Where is Carnegie Mellon?” A: “Pittsburgh, Pennsylvania, USA” Q: “Who is Jared Cohon?” A: “... is the current President of Carnegie Mellon University?” Q: “When was Herbert Simon born?” A: “15 June 1916” Question Answering Input Question Output Answers Google.

Classic “Pipelined” QA Architecture A sequence of discrete modules cascaded such that the output of the previous module is the input to the next module. Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction

Classic “Pipelined” QA Architecture Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Where was Andy Warhol born?

Classic “Pipelined” QA Architecture Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Where was Andy Warhol born? Discover keywords in the question, generate alternations, and determine answer type. Keywords: Andy (Andrew), Warhol, born Answer type: Location (City)

Classic “Pipelined” QA Architecture Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction Formulate IR queries using the keywords, and retrieve answer- bearing documents ( Andy OR Andrew ) AND Warhol AND born

Classic “Pipelined” QA Architecture Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction Extract answers of the expected type from retrieved documents. “Andy Warhol was born on August 6, 1928 in Pittsburgh and died February 22, 1927 in New York.” “Andy Warhol was born to Slovak immigrants as Andrew Warhola on August 6, 1928, on 73 Orr Street in Soho, Pittsburgh, Pennsylvania.”

Classic “Pipelined” QA Architecture Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction Answer cleanup and merging, consistency or constraint checking, answer selection and presentation. Pittsburgh 73 Orr Street in Soho, Pittsburgh, Pennsylvania New York 1. “Pittsburgh, Pennsylvania” 2. “New York” merge rank Pittsburgh, Pennsylvania select appropriate granularity

What is the cause of wrong answers? A pipelined QA system is only as good as its weakest module Poor retrieval and/or query formulation can result in low ranks for answer-bearing documents, or no answer-bearing documents retrieved Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction Failure point

What is Semantic Retrieval, and can it help? Semantic Retrieval is a broad term for a document retrieval technique that makes use of semantic information and language understanding Hypothesis: Use of Semantic Retrieval can improve performance, retrieving more, and more highly-ranked, relevant documents

What have other teams tried? LCC/SMU approach –Use an existing IR system as a black box; rich query expansion CL Research approach –Process top documents retrieved from an IR engine, extracting semantic relation triples, index and retrieve using RDBMS IBM (Prager) Predictive Annotation –Store answer types (QA-Tokens) in the IR system’s index, and retrieve on them

LCC/SMU Approach Syntactic relationships (controlled synonymy), morphological and derivational expansions for Boolean keywords Statistical passage extraction finds windows around keywords Semantic constraint check for filtering (unification) NE recognition and pattern matching as a third pass for answer extraction Ad hoc relevance scoring: term proximity, occurrence of answer in an apposition, etc Moldovan, et. al., Performance issues and error analysis in an open-domain QA system, ACM TOIS, vol. 21, no Passage Extraction IR Boolean query Documents Passages Keywords and Alternations Constraint Checking Named Entity Extraction Answer Candidates Extended Wordnet

Litkowski/CL Research Approach Relation triples: discourse entity (NP) + semantic role or relation + governing word; essentially similar to our predicates Unranked XPath querying against RDBMS Litkowski, K.C. Question Answering Using XML-Tagged Documents. TREC 2003 The quick brown fox jumped over the lazy dog. Docs RDBMS Sentences XML/xpath top PRISE documents jumped lazy dog quick brown fox entity mention canonicalization Semantic relationship triples

Predictive Annotation Textract identifies candidate answers at indexing time QA-Tokens are indexed as text items along with actual doc tokens Passage retrieval, with simple bag-of-words combo- match (heuristic) ranking formula Prager, et. al. Question-answering by predictive annotation. SIGIR 2000 Gasoline cost $0.78 per gallon in Docs IR Corpus Textract (IE/NLP) Answer type taxonomy QA-Tokens Gasoline cost $0.78 MONEY$ per gallon VOLUME$ in 1999 YEAR$.

How is JAVELIN using Semantic Retrieval? Annotate corpus with semantic content (e.g. predicates), and index this content At runtime, perform similar analysis on input questions to get predicate templates Maximal recall of documents that contain matching predicate instances Constraint checking at the answer extraction stage to filter out false positives and rank best matches Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI 2005.

Annotating and Indexing the Corpus Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI RDBMS Text IR Indexer Annotation Framework loves MaryJohn Predicate- Argument Structure ARG0 ARG1 loves Mary John Actual Index Content ARG0 ARG1

Retrieval on Predicate-Argument Structure Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Who does John love?"

Retrieval on Predicate-Argument Structure Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI Predicate-Argument Template ARG0ARG1 loves ?x Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Who does John love?" John

Retrieval on Predicate-Argument Structure Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI IR What the IR engine sees: ARG0ARG1 loves ?x Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Who does John love?" John “Frank loves Alice. John dislikes Bob." "John loves Mary.” Some Retrieved Documents:

Retrieval on Predicate-Argument Structure Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, AAAI RDBMS Input Question Output Answers Question Analysis Document Retrieval Post- Processing Answer Extraction “Who does John love?" “Frank loves Alice. John dislikes Bob." "John loves Mary.” X Matching Predicate Instance ARG0ARG1 loves Mary John “Mary” ARG0ARG1 loves Alice Frank ARG0ARG1 dislikes Bob John

How can we evaluate the impact of Semantic Retrieval on QA systems? Performance can be indirectly evaluated by measuring the performance of the end-to-end QA system while varying the document retrieval strategy employed, in one of two ways: –NIST-style comparative evaluation –Absolute evaluation against new test sets Direct analysis of document retrieval performance –Requires an assumption such as, “maximal recall of relevant documents translates to best end-to-end system performance”

NIST-style Comparative Evaluation Answer keys developed by pooling –All answers gathered by all systems are checked by a human to develop the answer key –Voorhees showed that the comparative orderings between systems are stable regardless of exhaustiveness of judgments –Answer keys from TREC evaluations are never suitable for post- hoc evaluation (nor were they intended to be), since they may penalize a new strategy for discovering good answers not in the original pool Manual scoring –Judging system output involves semantics (Voorhees 2003) –Abstract away from differences in vocabulary or syntax, and robustly handle paraphrase This is the same methodology used in the Definition QA evaluation in TREC 2003 and 2004

Absolute Evaluation Requires building new test collections –Not dependent on pooled results from systems, so suitable for post-hoc experimentation –Human effort is required; a methodology is described in (Katz and Lin 2005), (Bilotti, Katz and Lin 2004) and (Bilotti 2004) Automatic scoring methods based on n-grams, or fuzzy unification on predicate-argument structure (Lin and Demner-Fushman 2005), (Vandurme et al. 2003) can be applied Can evaluate at the level of documents or passages retrieved, predicates matched, or answers extracted, depending on the level of detail in the test set.

Preliminary Results: TREC 2005 Relationship QA Track 25 scenario-type questions; the first time such questions have occurred officially in the TREC QA track Semi-automatic runs were allowed: JAVELIN submitted a second run using manual question analysis Results (in MRR of relevant nuggets): –Run 1: –Run 2: Example on the next slide!

Example: Question Analysis The analyst is interested in Iraqi oil smuggling. Specifically, is Iraq smuggling oil to other countries, and if so, which countries? In addition, who is behind the Iraqi oil smuggling? interested Iraqi oil smuggling The analyst ARG0ARG1 smuggling oil Iraq ARG0 ARG1 other countries ARG2 smuggling oil Iraq ARG0 ARG1 which countries ARG2 is behind the Iraqi oil smuggling Who ARG0ARG1

Example: Results The analyst is interested in Iraqi oil smuggling. Specifically, is Iraq smuggling oil to other countries, and if so, which countries? In addition, who is behind the Iraqi oil smuggling? 1. “The amount of oil smuggled out of Iraq has doubled since August last year, when oil prices began to increase,” Gradeck said in a telephone interview Wednesday from Bahrain. 2. U.S.: Russian Tanker Had Iraqi Oil By ROBERT BURNS, AP Military Writer WASHINGTON (AP) – Tests of oil samples taken from a Russian tanker suspected of violating the U.N. embargo on Iraq show that it was loaded with petroleum products derived from both Iranian and Iraqi crude, two senior defense officials said. 5. With no American or allied effort to impede the traffic, between 50,000 and 60,000 barrels of Iraqi oil and fuel products a day are now being smuggled along the Turkish route, Clinton administration officials estimate. (7 of 15 relevant)

Where do we go from here? What to index and how to represent it –Moving to Indri 1 allows exact representation of our predicate structure in the index Building a Scenario QA test collection Query formulation and relaxation –Learning or planning strategies Ranking retrieved predicate instances –Aggregating information across documents Inference and evidence combination Extracting answers from predicate-argument structure 1.

References Bilotti. Query Expansion Techniques for Question Answering. Masters’ Thesis, MIT Bilotti, et. al. What Works Better for Question Answering: Stemming or Morphological Query Expansion? IR4QA workshop at SIGIR Lin and Demner-Fushman. Automatically Evaluating Answers to Definition Questions. HLT/EMNLP Litkowski, K.C. Question Answering Using XML-Tagged Documents. TREC Metzler and Croft. Combining the Language Model and Inference Network Approaches to Retrieval. Information Processing and Management Special Issue on Bayesian Networks and Information Retrieval, 40(5), , Metzler, et. al., Indri at TREC 2004: Terabyte Track. TREC Moldovan, et. al., Performance issues and error analysis in an open-domain question answering system, ACM TOIS, vol. 21, no Nyberg, et. al. “Extending the JAVELIN QA System with Domain Semantics”, Proceedings of the 20 th National Conference on Artificial Intelligence (AAAI 2005). Pradhan, S., et. al. Shallow Semantic Parsing using Support Vector Machines. HTL/NAACL Prager, et. al. Question-answering by predictive annotation. SIGIR Vandurme, B. et. al. Towards Light Semantic Processing for Question Answering. HLT/NAACL Voorhees, E. Overview of the TREC 2003 question answering track. TREC 2003.