From Question-Answering to Information-Seeking Dialogs Jerry R. Hobbs Artificial Intelligence Center SRI International Menlo Park, California (with Douglas.

Slides:



Advertisements
Similar presentations
Three-Step Database Design
Advertisements

DAML Queries/Life Cycle SRI International. Parts of Ontologies (used in the examples to follow) Assumptions Researcher String lastName firstName Publication-ref.
SWG Strategy (C) Copyright IBM Corp. 2006, All Rights Reserved. P4 Task 2 Fact Extraction using a CNL Current Status David Mott, Dave Braines, ETS,
Knowledge Creation Tools for DAML Grit Denker, Jerry R. Hobbs, David Martin Srini Narayanan, Richard Waldinger SRI International.
Modelling with expert systems. Expert systems Modelling with expert systems Coaching modelling with expert systems Advantages and limitations of modelling.
Proceedings of the Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2007) Learning for Semantic Parsing Advisor: Hsin-His.
Pointing at Places in a Geospatial Theory Richard Waldinger and Peter Jarvis Artificial Intelligence Center SRI International Jennifer Dungan Ecosystem.
Temporal Action Logic for Question Answering in an Adventure Game Temporal Action Logic for Question Answering in an Adventure Game Martin Magnusson and.
CSE 425: Logic Programming I Logic and Programs Most programs use Boolean expressions over data Logic statements can express program semantics –I.e., axiomatic.
Learning Networks connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning.
NaLIX: A Generic Natural Language Search Environment for XML Data Presented by: Erik Mathisen 02/12/2008.
Image Search Presented by: Samantha Mahindrakar Diti Gandhi.
1 CS 502: Computing Methods for Digital Libraries Lecture 20 Multimedia digital libraries.
Basi di dati distribuite Prof. M.T. PAZIENZA a.a
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
Automatically Constructing a Dictionary for Information Extraction Tasks Ellen Riloff Proceedings of the 11 th National Conference on Artificial Intelligence,
Employing Two Question Answering Systems in TREC 2005 Harabagiu, Moldovan, et al 2005 Language Computer Corporation.
Domain-Specific Software Engineering Alex Adamec.
1 Consistency Checking of Semantic Web Ontologies Kenneth Baclawski, Northeastern U. & VIS Mieczyslaw M. Kokar, Northeastern U. & VIS Richard Waldinger,
Semantic Interoperability Jérôme Euzenat INRIA & LIG France Natasha Noy Stanford University USA.
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
The Problem Finding information about people in huge text collections or on-line repositories on the Web is a common activity Person names, however, are.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Processing of large document collections Part 10 (Information extraction: multilingual IE, IE from web, IE from semi-structured data) Helena Ahonen-Myka.
Notes for Chapter 12 Logic Programming The AI War Basic Concepts of Logic Programming Prolog Review questions.
Institute of Informatics and Telecommunications – NCSR “Demokritos” Bootstrapping ontology evolution with multimedia information extraction C.D. Spyropoulos,
Some Thoughts on HPC in Natural Language Engineering Steven Bird University of Melbourne & University of Pennsylvania.
Ontologies Reasoning Components Agents Simulations Belief Update, Planning and the Fluent Calculus Jacques Robin.
EXCS Sept Knowledge Engineering Meets Software Engineering Hele-Mai Haav Institute of Cybernetics at TUT Software department.
Knowledge representation
CoGenTex, Inc. Ontology-based Multimodal User Interface in MOQA AQUAINT 18-Month Workshop San Diego, California Tanya Korelsky Benoit Lavoie Ted Caldwell.
Author: William Tunstall-Pedoe Presenter: Bahareh Sarrafzadeh CS 886 Spring 2015.
Artificial intelligence project
Machine Translation, Digital Libraries, and the Computing Research Laboratory Indo-US Workshop on Digital Libraries June 23, 2003.
Artificial Intelligence
Abstract Question answering is an important task of natural language processing. Unification-based grammars have emerged as formalisms for reasoning about.
From Question-Answering to Information-Seeking Dialogs Jerry R. Hobbs USC Information Sciences Institute Marina del Rey, California (with Chris Culy, Douglas.
EU Project proposal. Andrei S. Lopatenko 1 EU Project Proposal CERIF-SW Andrei S. Lopatenko Vienna University of Technology
June 12, 2003AQUAINT 18 Month Meeting San Diego CA Natural Language Querying of the Semantic Web SRI International Information Science Institute.
Chapter 6 Programming Languages (2) Introduction to CS 1 st Semester, 2015 Sanghyun Park.
TOPIC CENTRIC QUERY ROUTING Research Methods (CS689) 11/21/00 By Anupam Khanal.
An Intelligent Analyzer and Understander of English Yorick Wilks 1975, ACM.
From Question-Answering to Information-Seeking Dialogs Jerry R. Hobbs USC/ISI Marina del Rey, CA with Douglas Appelt, David Israel, Peter Jarvis, David.
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.
LIS618 lecture 3 Thomas Krichel Structure of talk Document Preprocessing Basic ingredients of query languages Retrieval performance evaluation.
Sheila McIlraith, Knowledge Systems Lab DAML Kickoff 08/14/00 Mobilizing the Web with DAML-Enabled Web Services Services Team Sheila McIlraith (Technical.
©Ferenc Vajda 1 Semantic Grid Ferenc Vajda Computer and Automation Research Institute Hungarian Academy of Sciences.
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.
Using Several Ontologies for Describing Audio-Visual Documents: A Case Study in the Medical Domain Sunday 29 th of May, 2005 Antoine Isaac 1 & Raphaël.
AQUAINT Kickoff Meeting Advanced Techniques for Answer Extraction and Formulation Language Computer Corporation Dallas, Texas.
For Monday Read chapter 26 Last Homework –Chapter 23, exercise 7.
Introduction to Prolog. Outline What is Prolog? Prolog basics Prolog Demo Syntax: –Atoms and Variables –Complex Terms –Facts & Queries –Rules Examples.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
HITIQA: Scenario Based Question Answering Tomek Strzalkowski, et al The State University of New York at Albany Paul Kantor, et al Rutgers University Boris.
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
Formal Verification. Background Information Formal verification methods based on theorem proving techniques and model­checking –To prove the absence of.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Artificial Intelligence Midterm 고려대학교 컴퓨터학과 자연어처리 연구실 임 해 창.
For Monday Read chapter 26 Homework: –Chapter 23, exercises 8 and 9.
AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
MDD-Kurs / MDA Cortex Brainware Consulting & Training GmbH Copyright © 2007 Cortex Brainware GmbH Bild 1Ver.: 1.0 How does intelligent functionality implemented.
OKBC (Open Knowledge Base Connectivity) An API For Knowledge Servers
Architecture Components
Knowledge Representation
KNOWLEDGE REPRESENTATION
Lecture 8 Information Retrieval Introduction
Representations & Reasoning Systems (RRS) (2.2)
Presentation transcript:

From Question-Answering to Information-Seeking Dialogs Jerry R. Hobbs Artificial Intelligence Center SRI International Menlo Park, California (with Douglas Appelt, Chris Culy, David Israel, David Martin, Martin Reddy, Mark Stickel, and Richard Waldinger)

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International2 Key Ideas 1. Logical analysis/decomposition of questions into component questions, using a reasoning engine 2. Bottoming out in variety of web resources and information extraction engine 3. Use of component questions to drive subsequent dialogue, for elaboration, revision, and clarification 4. Use of analysis of questions to determine, formulate, and present answers.

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International3 Plan of Attack Inference-Based System: Inference for Question-Answering -- this year Inference for Dialog Structure -- next year, but starting design this year Document retrieval and information extraction for question-answering: Incorporate as resource in inference-based system -- this year

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International4 Composition of Information from Multiple Sources How far is it from Mascat to Kandahar? What is the lat/long of Mascat? What is the distance between the two lat/longs? What is the lat/long of Kandahar? Alexandrian Digital Library Gazetteer Geographical Formula or Question Decomposition via Logical Rules Resources Attached to Reasoning Process Alexandrian Digital Library Gazetteer GEMINI SNARK

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International5 Composition of Information from Multiple Sources Show me the region 100 km north of the capital of Afghanistan. What is the capital of Afghanistan? What is the lat/long 100 km north? What is the lat/long of Kabul? CIA Fact Book Geographical Formula Question Decomposition via Logical Rules Alexandrian Digital Library Gazetteer Show that lat/long Terravision Resources Attached to Reasoning Process

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International6 Combining Time, Space, and Personal Information Could Mohammed Atta have met with an Iraqi official between 1998 and 2001? IE Engine Geographical Reasoning Question Decomposition via Logical Rules Resource Attached to Reasoning Process meet(a,b,t) & 1998  t  2001 at(a,x 1,t) & at(b,x 2,t) & near(x 1,x 2 ) & official(b,Iraq) go(a,x 1,t)go(b,x 2,t) IE Engine Temporal Reasoning Logical Form

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International7 Two Central Systems GEMINI: Large unification grammar of English Under development for more than a decade Fast parser Generates logical forms Used in ATIS and CommandTalk SNARK: Large, efficient theorem prover Under development for more than a decade Built-in temporal and spatial reasoners Procedural attachment, incl for web resources Extracts answers from proofs Strategic controls for speed-up

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International8 Linguistic Variation How far is Mascat from Kandahar? How far is it from Mascat to Kandahar? How far is it from Kandahar to Mascat? How far is it betweeen Mascat and Kandahar? What is the distance from Mascat to Kandahar? What is the distance between Mascat and Kandahar? GEMINI parses and produces logical forms for most TREC-type queries Use TACITUS and FASTUS lexicons to augment GEMINI lexicon Unknown word guessing based on "morphology" and immediate context

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International9 "Snarkification" Problem: GEMINI produces logical forms not completely aligned with what SNARK theories need Current solution: Write simplification code to map from one to the other Long-term solution: Logical forms that are aligned better

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International10 Relating Lexical Predicates to Core Theory Predicates "... distance..." "how far..." distance-between Need to write these axioms for every domain we deal with Have illustrative examples

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International11 Decomposition of Questions lat-long(l 1,x) & lat-long(l 2,y) & lat-long-distance(d,l 1,l 2 ) --> distance-between(d,x,y) Need axioms relating core theory predicates and predicates from available resources Have illustrative examples

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International12 Procedural Attachment Declaration for certain predicates: There is a procedure for proving it Which arguments are required before called lat-long(l 1,x) lat-long-distance(d,l 1,l 2 ) When predicate with those arguments bound is generated in proof, procedure is exectuted.

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International13 Open Agent Architecture OAA Agent GEMINI snarkify SNARK Resources via OAA Agents

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International14 Use of SMART + TextPro Question Subquestion-1 Other Resources Question Decomposition via Logical Rules Resources Attached to Reasoning Process Subquestion-2 Subquestion-3 SMART + TextPro One Resource Among Many

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International15 Information Extraction Engine as a Resource SMART: Document retrieval for pre-processing TextPro: Top of the line information extraction engine Analyze NL query w GEMINI and SNARK Run TextPro over documents retrieved by SMART Retrieve best-match passage Use TextPro annotations or GEMINI analysis to extract answer from passage

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International16 Linking SNARK with TextPro TextSearch(EntType(?x), Terms(p), Terms(c), WSeq) & Analyze(WSeq, p(?x,c)) --> p(?x,c) Call to SMART+TextPro Type of questioned constituent Synonyms and hypernyms of word associated with p or c Answer: Ordered sequence of strings of words Match pieces of answer strings with pieces of query Subquery generated by SNARK during analysis of query

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International17 Information Extraction Engine as a Resource SMART: Document retrieval for pre-processing TextPro: Top of the line information extraction engine Analyze NL query w GEMINI and SNARK Run TextPro over documents retrieved by SMART TextPro returns relevant templates Agent turns templates into logic for SNARK to use in proof

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International18 Domain-Specific Patterns Decide upon domain (e.g., nonproliferation) Compile list of principal properties and relations of interest Implement these patterns in TextPro Implement link between TextPro and SNARK, converting between templates and logic

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International19 Temporal Reasoning: Structure Topology of Time: start, end, before, between Measures of Duration: for an hour,... Clock and Calendar: 3:45pm, Wednesday, June 12 Temporal Aggregates: every other Wednesday Deictic Time: last year,...

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International20 Temporal Reasoning: Goals Develop temporal ontology (DAML) Reason about time in SNARK (AQUAINT, DAML) Link with Temporal Annotation Standards (AQUAINT) Answer questions with temporal component (AQUAINT) Nearly complete In progress

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International21 Spatial and Geographical Reasoning: Structure Topology of Space: Is Albania a part of Europe? Dimensionality Measures: How large is North Korea? Orientation and Shape: What direction is Monterey from SF? Latitude and Longitude: Alexandrian Digital Library Gazetteer Political Divisions: CIA World Fact Book,...

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International22 Spatial and Geographical Reasoning: Goals Develop spatial and geographical ontology (DAML) Reason about space and geography in SNARK (AQUAINT, DAML) Attach spatial and geographical resources (AQUAINT) Answer questions with spatial component (AQUAINT) Some capability now

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International23 Dialog Modeling Key Idea: System matches user's utterance with one of several active tasks. Understanding dialog is one active task. Rules of form: property(situation) --> active(Task 1 ) including utter(u,w) --> active(DialogTask) want(u,Task 1 ) --> active(Task 1 ) Understanding is matching utterance (conjunction of predications) with an active task or the condition of an inactive task.

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International24 Dialog Task Model understand(a,e,t): hear(a,w) & parse(w,e) & match(e,t) yes Action determined by utterance and task no -- x unmatched Ask about x

05/15/02Principal Investigator: Jerry R. Hobbs, SRI International25 Fixed-Domain QA Evaluation Pick a domain, e.g., nonproliferation Pick a set of resources, including a corpus of texts, structured databases, web services Have expert make up 200+ realistic questions, answerable with resources + inference Divide questions into training and test sets Give sites one month+ to work on training set Test on test set