Is Question Answering an Acquired Skill? Soumen Chakrabarti G. Ramakrishnan D. Paranjpe P. Bhattacharyya IIT Bombay.

Slides:



Advertisements
Similar presentations
An Ontology Creation Methodology: A Phased Approach
Advertisements

School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
ThemeInformation Extraction for World Wide Web PaperUnsupervised Learning of Soft Patterns for Generating Definitions from Online News Author Cui, H.,
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
University of Sheffield NLP Module 4: Machine Learning.
Specialized models and ranking for coreference resolution Pascal Denis ALPAGE Project Team INRIA Rocquencourt F Le Chesnay, France Jason Baldridge.
CPSC 502, Lecture 15Slide 1 Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 15 Nov, 1, 2011 Slide credit: C. Conati, S.
Automatic indexing and retrieval of crime-scene photographs Katerina Pastra, Horacio Saggion, Yorick Wilks NLP group, University of Sheffield Scene of.
Ang Sun Ralph Grishman Wei Xu Bonan Min November 15, 2011 TAC 2011 Workshop Gaithersburg, Maryland USA.
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Is Question Answering an Acquired Skill? Soumen Chakrabarti IIT Bombay With Ganesh Ramakrishnan Deepa Paranjpe Pushpak Bhattacharyya.
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.
Inducing Information Extraction Systems for New Languages via Cross-Language Projection Ellen Riloff University of Utah Charles Schafer, David Yarowksy.
Using Information Extraction for Question Answering Done by Rani Qumsiyeh.
1 SIMS 290-2: Applied Natural Language Processing Marti Hearst Sept 22, 2004.
Learning syntactic patterns for automatic hypernym discovery Rion Snow, Daniel Jurafsky and Andrew Y. Ng Prepared by Ang Sun
Techniques Used in Modern Question-Answering Systems Candidacy Exam Elena Filatova December 11, 2002 Committee Luis GravanoColumbia University Vasileios.
1 Natural Language Processing for the Web Prof. Kathleen McKeown 722 CEPSR, Office Hours: Wed, 1-2; Tues 4-5 TA: Yves Petinot 719 CEPSR,
Finding Advertising Keywords on Web Pages Scott Wen-tau YihJoshua Goodman Microsoft Research Vitor R. Carvalho Carnegie Mellon University.
A Web-based Question Answering System Yu-shan & Wenxiu
Mining and Summarizing Customer Reviews
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Probabilistic Model for Definitional Question Answering Kyoung-Soo Han, Young-In Song, and Hae-Chang Rim Korea University SIGIR 2006.
1 A study on automatically extracted keywords in text categorization Authors:Anette Hulth and Be´ata B. Megyesi From:ACL 2006 Reporter: 陳永祥 Date:2007/10/16.
Survey of Semantic Annotation Platforms
Reyyan Yeniterzi Weakly-Supervised Discovery of Named Entities Using Web Search Queries Marius Pasca Google CIKM 2007.
Interpreting Dictionary Definitions Dan Tecuci May 2002.
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.
Lecture 6 Hidden Markov Models Topics Smoothing again: Readings: Chapters January 16, 2013 CSCE 771 Natural Language Processing.
A Probabilistic Graphical Model for Joint Answer Ranking in Question Answering Jeongwoo Ko, Luo Si, Eric Nyberg (SIGIR ’ 07) Speaker: Cho, Chin Wei Advisor:
1 Query Operations Relevance Feedback & Query Expansion.
Structured Use of External Knowledge for Event-based Open Domain Question Answering Hui Yang, Tat-Seng Chua, Shuguang Wang, Chun-Keat Koh National University.
21/11/2002 The Integration of Lexical Knowledge and External Resources for QA Hui YANG, Tat-Seng Chua Pris, School of Computing.
Knowledge Modeling, use of information sources in the study of domains and inter-domain relationships - A Learning Paradigm by Sanjeev Thacker.
Date: 2014/02/25 Author: Aliaksei Severyn, Massimo Nicosia, Aleessandro Moschitti Source: CIKM’13 Advisor: Jia-ling Koh Speaker: Chen-Yu Huang Building.
Question Answering over Implicitly Structured Web Content
Collocations and Information Management Applications Gregor Erbach Saarland University Saarbrücken.
WIRED Week 3 Syllabus Update (next week) Readings Overview - Quick Review of Last Week’s IR Models (if time) - Evaluating IR Systems - Understanding Queries.
A Novel Pattern Learning Method for Open Domain Question Answering IJCNLP 2004 Yongping Du, Xuanjing Huang, Xin Li, Lide Wu.
A Scalable Machine Learning Approach for Semi-Structured Named Entity Recognition Utku Irmak(Yahoo! Labs) Reiner Kraft(Yahoo! Inc.) WWW 2010(Information.
Enhanced Answer Type Inference from Questions using Sequential Models Vijay Krishnan Sujatha Das Soumen Chakrabarti IIT Bombay.
CSKGOI'08 Commonsense Knowledge and Goal Oriented Interfaces.
Is Question Answering an Acquired Skill? Soumen Chakrabarti IIT Bombay With Ganesh Ramakrishnan Deepa Paranjpe Vijay Krishnan Arnab Nandi.
Information Retrieval using Word Senses: Root Sense Tagging Approach Sang-Bum Kim, Hee-Cheol Seo and Hae-Chang Rim Natural Language Processing Lab., Department.
Supertagging CMSC Natural Language Processing January 31, 2006.
A Classification-based Approach to Question Answering in Discussion Boards Liangjie Hong, Brian D. Davison Lehigh University (SIGIR ’ 09) Speaker: Cho,
Mining Dependency Relations for Query Expansion in Passage Retrieval Renxu Sun, Chai-Huat Ong, Tat-Seng Chua National University of Singapore SIGIR2006.
4. Relationship Extraction Part 4 of Information Extraction Sunita Sarawagi 9/7/2012CS 652, Peter Lindes1.
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
Acquisition of Categorized Named Entities for Web Search Marius Pasca Google Inc. from Conference on Information and Knowledge Management (CIKM) ’04.
Using Wikipedia for Hierarchical Finer Categorization of Named Entities Aasish Pappu Language Technologies Institute Carnegie Mellon University PACLIC.
Exploiting Named Entity Taggers in a Second Language Thamar Solorio Computer Science Department National Institute of Astrophysics, Optics and Electronics.
©2012 Paula Matuszek CSC 9010: Information Extraction Overview Dr. Paula Matuszek (610) Spring, 2012.
SEMANTIC VERIFICATION IN AN ONLINE FACT SEEKING ENVIRONMENT DMITRI ROUSSINOV, OZGUR TURETKEN Speaker: Li, HueiJyun Advisor: Koh, JiaLing Date: 2008/5/1.
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.
Learning Analogies and Semantic Relations Nov William Cohen.
Learning Event Durations from Event Descriptions Feng Pan, Rutu Mulkar, Jerry R. Hobbs University of Southern California ACL ’ 06.
Feature Assignment LBSC 878 February 22, 1999 Douglas W. Oard and Dagobert Soergel.
Instance Discovery and Schema Matching With Applications to Biological Deep Web Data Integration Tantan Liu, Fan Wang, Gagan Agrawal {liut, wangfa,
Selecting Relevant Documents Assume: –we already have a corpus of documents defined. –goal is to return a subset of those documents. –Individual documents.
Integrating linguistic knowledge in passage retrieval for question answering J¨org Tiedemann Alfa Informatica, University of Groningen HLT/EMNLP 2005.
Relation Extraction (RE) via Supervised Classification See: Jurafsky & Martin SLP book, Chapter 22 Exploring Various Knowledge in Relation Extraction.
Automatic Detection of Causal Relations for Question Answering
Introduction to Information Retrieval
CS246: Information Retrieval
Template-based Question Answering over RDF Data
Topic: Semantic Text Mining
Introduction to Search Engines
Extracting Why Text Segment from Web Based on Grammar-gram
Presentation transcript:

Is Question Answering an Acquired Skill? Soumen Chakrabarti G. Ramakrishnan D. Paranjpe P. Bhattacharyya IIT Bombay

QAChakrabarti3 Web search and QA Information need – words relating things + thing aliases = telegraphic Web queries Cheapest laptop with wireless best price laptop Why is the sky blue? sky blue reason When was the Space Needle built? Space Needle history Entity and relation extraction technology better than ever (SemTag, KnowItAll) Ontology extension (e.g., is a kind of) List extraction (e.g., is an instance of) Slot-filling (author X wrote book Y)

QAChakrabarti4 Factoid QA Specialize given domain to a token related to ground constants in the query What animal is Winnie the Pooh? hyponym(animal) NEAR Winnie the Pooh When was television invented? instance-of(time) NEAR television NEAR synonym(invented) Three kinds of useful question tokens Appear unchanged in passage (selector) Specialize to answer tokens (atype) Improve belief in answer via synonymy etc.

QAChakrabarti5 A new relational view of QA Entity class or atype may be expressed by A finite IS-A hierarchy (e.g. WordNet, TAP) A surface pattern matching infinitely many strings (e.g. digit+, Xx+, preceded by a preposition) Match selectors, specialize atype to answer tokens QuestionAtype clues Selectors Answer passage Question words Landing zone Direct syntactic match Entity class IS-A Limit search to certain rows Locate which column to read Landing zone Attribute or column name

QAChakrabarti6 Benefits of the relational view Scaling up by dumbing down Next stop after vector-space Far short of real knowledge representation and inference Barely getting practical at (near) Web scale Can set up as a learning problem: train with questions and answers embedded in passage context Transparent, self-tuning, easy to deploy Feature extractors used in entity taggers Relational/graphical learning on features

QAChakrabarti7 Subproblems Identify atype clues Easy: who, when, where, how many, how tall… Harder: What…, which…, name… Map atype clues to likely entity classes Data- and task-driven question classification Train quickly on new corpus and QA samples Identify selectors for keyword query Based on question context and global stats Get candidate passages from IR system Re-rank candidate passages

QAChakrabarti8 Mapping self-evident atypes Who person, when time, where place Not always trivial: how_many vs. when Question classification + handcrafted map Needs task knowledge and skilled effort Laborious to move to new corpus, language… Task-driven information extraction Enough info in training QA pairs to learn map Map clue to a generalization of the answer Surface patterns: hasDigit, [in] DDDD, NNP, CD WordNet-based: region#n#3, quantity#n#1

QAChakrabarti9 Mapping examples howwho fastmanyfarrich wrotefirst How fast can a cheetah run? A cheetah can chase its prey at up to 90 km/h How fast does light travel? Nothing moves faster than 186,000 miles per hour, the speed of light rate#n#2 abstraction#n#6 NNS rate#n#2 magnitude_relation#n#1 mile#n#3 linear_unit#n#1 measure#n#3 definite_quantity#n#1 paper_money#n#1 currency#n#1 writer, composer, artist, musician NNP, person explorer WordNet

QAChakrabarti10 What…, which…, name… atype clues Assumption: Question sentence has a wh- word and a main/auxiliary verb Observation: Atype clues are embedded in a noun phrase (NP) adjoining the main or auxiliary verb Heuristic: Atype clue = head of this NP Use a shallow parser and apply rule Head can have attributes Which (American (general)) is buried in Salzburg? Name (Saturns (largest (moon)))

QAChakrabarti11 Atype clue extraction stats Simple heuristic surprisingly effective If successful, extracted atype is mapped to WordNet synset (moon celestial body etc.) If no atype of this form available, try the self- evident atypes (who, when, where, how_X etc.)

QAChakrabarti12 Learning selectors Which question words are likely to appear (almost) unchanged in an answer passage? Constants in select-clauses of SQL queries Guides backoff policy for keyword query Local and global features POS of word, POS of adjacent words, case info, proximity to wh-word Suppose word is associated with synset set S NumSense: size of S (how polysemous is the word?) NumLemma: average #lemmas describing s S

QAChakrabarti13 Selector results Decision trees better than logistic regression F1=81% as against LR F1=75% Intuitive decision branches But logistic regression gives scores for query backoff Global features (IDF, NumSense, NumLemma) essential for accuracy Best F1 accuracy with local features alone: 7173% With local and global features: 81%

QAChakrabarti14 Putting together a QA system QA System Wordnet POS Tagger Training Corpus Shallow parser Learning tools N-E Tagger

QAChakrabarti15 Question Passage Index Corpus Sentence splitter Passage indexer Candidate passage Keyword query Keyword query generator Shallow Parser Noun and verb markers Atype Extractor Atype clues Learning to rerank passages Sample features: Do selectors match? How many? Is some non-selector passage token a specialization of the questions atype clue? Min, avg linear token distance between candidate token and matched selectors Learning to rerank passages Sample features: Do selectors match? How many? Is some non-selector passage token a specialization of the questions atype clue? Min, avg linear token distance between candidate token and matched selectors Logistic Regression Reranked passages Putting together a QA system Tokenizer POS Tagger Tagged question Tokenizer POS Tagger Entity Extractor Tagged passage Selector Learner Is QA pair?

QAChakrabarti16 Learning to re-rank passages Remove passage tokens matching selectors User already knows these are in passage Find passage token/s specializing atype For each candidate token collect Atype of question, original rank of passage Min, avg linear distances to matched selectors POS and entity tag of token if available Ushuaia, a port of about 30,000 dwellers set between the Beagle Channel and … How many inhabitants live in the town of Ushuaia selector match Surface pattern hasDigits WordNet match 5 tokens apart1

QAChakrabarti17 Effect of re-ranking results Categorical and numeric attributes Logistic regression Good precision, poor recall Use logit score to re-rank passages Rank of first correct passage shifts substantially Log scale

QAChakrabarti18 Mean reciprocal rank studies n q = smallest rank among answer passages Re-ranking reduces n q drastically MRR = (1/|Q |) q Q (1/n q ) Substantial gain in MRR TREC 2000 top MRRs:

QAChakrabarti19 Generalization across corpora Across-year numbers close to train/test split on a single year Features and model seem to capture corpus- independent linguistic Q+A artifacts

QAChakrabarti20 Re-ranking benefits by question type All question types benefit from re- ranking Benefits differ by question type Large benefits for what and which questions, thanks to WordNet Without WordNet customization

QAChakrabarti21 Conclusion A clean-room view of QA as feature extraction plus learning Recover structure info from question Learn correlations between question structure and passage features Competitive accuracy with negligible domain expertise or manual intervention Ongoing work Use redundancy available from the Web Model how selector and atype are related Treat all question types uniformly