AQUAINT Kickoff Meeting Advanced Techniques for Answer Extraction and Formulation Language Computer Corporation www.languagecomputer.com Dallas, Texas.

Slides:



Advertisements
Similar presentations
Dr. Leo Obrst MITRE Information Semantics Information Discovery & Understanding Command & Control Center February 6, 2014February 6, 2014February 6, 2014.
Advertisements

Taxonomy & Ontology Impact on Search Infrastructure John R. McGrath Sr. Director, Fast Search & Transfer.
Some Prolog Prolog is a logic programming language
COGEX at the Second RTE Marta Tatu, Brandon Iles, John Slavick, Adrian Novischi, Dan Moldovan Language Computer Corporation April 10 th, 2006.
Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,
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
Semantics For the Semantic Web: The Implicit, the Formal and The Powerful Amit Sheth, Cartic Ramakrishnan, Christopher Thomas CS751 Spring 2005 Presenter:
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
BioText Infrastructure Ariel Schwartz Gaurav Bhalotia 10/07/2002.
Basic IR Concepts & Techniques ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.
Employing Two Question Answering Systems in TREC 2005 Harabagiu, Moldovan, et al 2005 Language Computer Corporation.
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Information Retrieval in Practice
Amarnath Gupta Univ. of California San Diego. An Abstract Question There is no concrete answer …but …
OMAP: An Implemented Framework for Automatically Aligning OWL Ontologies SWAP, December, 2005 Raphaël Troncy, Umberto Straccia ISTI-CNR
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
1 Advanced Techniques for Answer Extraction and Formulation Language Computer Corporation Dallas, Texas PI: Dan Moldovan
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 The BT Digital Library A case study in intelligent content management Paul Warren
Steps Toward an AGI Roadmap Włodek Duch ( Google: W. Duch) AGI, Memphis, 1-2 March 2007 Roadmaps: A Ten Year Roadmap to Machines with Common Sense (Push.
Automatic Answer Validation in Open-Domain Question Answering Hristo Tanev TCC,ITC - IRST.
Learning Object Metadata Mining Masoud Makrehchi Supervisor: Prof. Mohamed Kamel.
1 QA for the Web Language Computer Corporation Dallas, Texas PI: Dan Moldovan
CoGenTex, Inc. Ontology-based Multimodal User Interface in MOQA AQUAINT 18-Month Workshop San Diego, California Tanya Korelsky Benoit Lavoie Ted Caldwell.
Question Answering.  Goal  Automatically answer questions submitted by humans in a natural language form  Approaches  Rely on techniques from diverse.
Of 33 lecture 10: ontology – evolution. of 33 ece 720, winter ‘122 ontology evolution introduction - ontologies enable knowledge to be made explicit and.
Carnegie Mellon School of Computer Science Copyright © 2001, Carnegie Mellon. All Rights Reserved. JAVELIN Project Briefing 1 AQUAINT Phase I Kickoff December.
1 Information Retrieval Acknowledgements: Dr Mounia Lalmas (QMW) Dr Joemon Jose (Glasgow)
SEMANTIC ANALYSIS WAES3303
QUALIFIER in TREC-12 QA Main Task Hui Yang, Hang Cui, Min-Yen Kan, Mstislav Maslennikov, Long Qiu, Tat-Seng Chua School of Computing National University.
1 Just-in-Time Interactive Question Answering Language Computer Corporation Sanda Harabagiu, PI John Lehmann John Williams Paul Aarseth.
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.
BAA - Big Mechanism using SIRA Technology Chuck Rehberg CTO at Trigent Software and Chief Scientist at Semantic Insights™
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.
Artificial Intelligence Research Center Pereslavl-Zalessky, Russia Program Systems Institute, RAS.
Next Generation Search Engines Ehsun Daroodi 1 Feb, 2003.
Bloom’s Critical Thinking Questioning Strategies A Guide to Higher Level Thinking Ruth SundaKyrene de las Brisas.
Trustworthy Semantic Webs Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #4 Vision for Semantic Web.
AQUAINT June 2002 Workshop June 2002 Just-in-Time Interactive Question Answering Sanda Harabagiu: PI Language Computer Corporation.
Of 33 lecture 1: introduction. of 33 the semantic web vision today’s web (1) web content – for human consumption (no structural information) people search.
MODEL-BASED SOFTWARE ARCHITECTURES.  Models of software are used in an increasing number of projects to handle the complexity of application domains.
Introduction to Information Retrieval Example of information need in the context of the world wide web: “Find all documents containing information on computer.
Digital Libraries1 David Rashty. Digital Libraries2 “A library is an arsenal of liberty” Anonymous.
Information Retrieval
Some Thoughts to Consider 8 How difficult is it to get a group of people, or a group of companies, or a group of nations to agree on a particular ontology?
Comparing Document Segmentation for Passage Retrieval in Question Answering Jorg Tiedemann University of Groningen presented by: Moy’awiah Al-Shannaq
Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent.
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.
Relevance Models and Answer Granularity for Question Answering W. Bruce Croft and James Allan CIIR University of Massachusetts, Amherst.
8 December 1997Industry Day Applications of SuperTagging Raman Chandrasekar.
Strategies for Advanced Question Answering Sanda Harabagiu & Finley Lacatusu Language Computer Corporation HLT-NAACL2004 Workshop.
1 CS 8803 AIAD (Spring 2008) Project Group#22 Ajay Choudhari, Avik Sinharoy, Min Zhang, Mohit Jain Smart Seek.
NTNU Speech Lab 1 Topic Themes for Multi-Document Summarization Sanda Harabagiu and Finley Lacatusu Language Computer Corporation Presented by Yi-Ting.
AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
CS 4700: Foundations of Artificial Intelligence
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Multimedia Information Retrieval
ece 627 intelligent web: ontology and beyond
Automatic Detection of Causal Relations for Question Answering
CSE 635 Multimedia Information Retrieval
CS246: Information Retrieval
Presentation transcript:

AQUAINT Kickoff Meeting Advanced Techniques for Answer Extraction and Formulation Language Computer Corporation Dallas, Texas PI: Dan Moldovan

AQUAINT Kickoff Meeting - AnsQA Advanced Techniques for Answer Extraction and Formulation  People Dan Moldovan, PI Sanda Harabagiu, Co-PI Mihai Surdeanu Marius Pasca John Lehmann Vasile Rus Earl Hood

AQUAINT Kickoff Meeting - AnsQA Tasks  Task 1. QA System Taxonomy  Task 2. Answer fusion  Task 3. Develop methods for on-line ontology construction  Task 4. Develop an inference engine capable of providing answer justification  Task 5. Formulate concise and coherent answers  Task 6. Explore new QA System Architectures.

AQUAINT Kickoff Meeting - AnsQA T1: QA System Taxonomy  Need for a taxonomy  Goal: Develop elaborate taxonomies for QA systems and applications  Approach: Develop QA System theoretical models Study tradeoffs and theoretical limits

AQUAINT Kickoff Meeting - AnsQA T1: QA System Taxonomy  Model QA system performance as a function of: Question space: scope, context, judgement Answer space: multiple-sources, fusion, interpretations Document space: type, indexing System architecture: modules, feedbacks Computing power: processing time, computer parameters Resources used: dictionaries, knowledge bases, knowledge acquisition, parsers, theorem provers

AQUAINT Kickoff Meeting - AnsQA T2: Answer Fusion  Goal: Develop methods to handle questions whose answers spread across several documents.  Approach: Map the original question into simpler queries Collect answers to these simple queries Ensemble an answer by fusing partial answers.

AQUAINT Kickoff Meeting - AnsQA T2: Answer Fusion  Study answer fusion at various levels of complexity Questions asking simple facts What countries import sugar from Cuba? Questions that require on-line ontology development What software products does Microsoft sell? What causes asthma? What are the effects of alcohol on the brain? Speculative questions about future events Does the Fed cut the interest rate at their next meeting?

AQUAINT Kickoff Meeting - AnsQA T2: Answer Fusion Use IE and Text Mining to map semantic relations into lexico-syntactic patterns that in turn help to develop ontologies. Q: What causes asthma?

AQUAINT Kickoff Meeting - AnsQA T3: On-line Ontology Development  Goal: Develop automatically ontological structures that help answer some complex questions  Approach: Use knowledge acquisition from text methods to extract and classify concepts and relations relevant to question keywords

AQUAINT Kickoff Meeting - AnsQA T3: On-line Ontology Development  Example: What software products does Microsoft sell?

AQUAINT Kickoff Meeting - AnsQA T4: Answer Justification  Goal: Develop an inference engine capable of justifying an answer via a logical proof  Approach: Transform questions and document paragraphs into logical representations Use world knowledge axioms extracted from WordNet glosses Construct lexical chains between query concepts and candidate answer sentence concepts Apply unification on lexical chains.

AQUAINT Kickoff Meeting - AnsQA T4: Answer Justification Logic proof for P2 succeeds and agent of shooting Sheriff_Pat_Garret unifies with PERSON e1 = e1’ x1 = x2’ x2 = x1’ P1: The scene called for Phillips’ character to be saved from a lynching when Billy the Kid (Emilio Estevez) shot the rope in half just as he was about to be hanged. P2: In 1881, outlaw William H. Bonney Jr., alias Billy the Kid, was shot and killed by Sheriff Pat Garrett in Fort Summer, N.M. Example Q481: Who shot Billy the Kid? LFT:

AQUAINT Kickoff Meeting - AnsQA T4: Answer Justification WordNet axioms: Columbian: of Columbia murder: kill intentionally with premeditation kill: cause to die A: “Several gunmen on a highway leading to the Columbian city of Ibaque murdered Colombian ambassador to Honduras Lucelly Garcia today.” Example Q045: When did Lucelly Garcia, former ambassador of Columbia to Honduras die?

AQUAINT Kickoff Meeting - AnsQA T5: Answer formulation  Goal: Develop methods to formulate concise and coherent answers  Approach: Answer formulation receives inputs from answer extraction, dialogue, and other modules. Language generation operators piece together the information provided by the answer elements.

AQUAINT Kickoff Meeting - AnsQA T5: Answer formulation

AQUAINT Kickoff Meeting - AnsQA T5: Answer formulation  Example: How do trade liberalization and foreign aid affect international migration?

AQUAINT Kickoff Meeting - AnsQA T6: Explore new QA System Architectures  Goal: Study innovative QA system architectures that are high performance, modular, and tunable.  Approach: Study via analytical modeling, simulations and implementation the architectural implications of features such as: High recall High precision Fast response time Portability Large volume and diversity of documents