Generation of Referring Expressions: the State of the Art SELLC Winter School, Guangzhou 2010 Kees van Deemter Computing Science University of Aberdeen.

Slides:



Advertisements
Similar presentations
Reference Resolution And Cognitive Grammar Susanne Salmon-Alt Laurent Romary Loria - Nancy, France ICCS-01 San Sebastian, May 2001.
Advertisements

Kees van Deemter Matthew Stone Formal Issues in Natural Language Generation Lecture 4 Shieber 1993; van Deemter 2002.
A very short introduction to Natural Language Generation Kees van Deemter Computing Science University of Aberdeen.
Generation of Referring Expressions: Managing Structural Ambiguities I.H. KhanG. Ritchie K. van Deemter University of Aberdeen, UK.
Some common assumptions behind Computational Generation of Referring Expressions (GRE) (Introductory remarks at the start of the workshop)
Kees van Deemter Matthew Stone Formal Issues in Natural Language Generation Lecture 5 Stone, Doran,Webber, Bleam & Palmer.
Generation of Referring Expressions (GRE) Reading: Dale & Reiter (1995) (key paper in this area)
SELLC Winter School 2010 Evaluating Algorithms for GRE Kees van Deemter (work with Albert Gatt, Ielka van der Sluis, and Richard Power) University of Aberdeen,
Conceptual coherence in the generation of referring expressions Albert Gatt & Kees van Deemter University of Aberdeen {agatt,
Generation of Referring Expressions: the State of the Art SELLC Summer School, Harbin 2010 Kees van Deemter Computing Science University of Aberdeen.
Charting the Potential of Description Logic for the Generation of Referring Expression SELLC, Guangzhou, Dec Yuan Ren, Kees van Deemter and Jeff.
Generation of Referring Expressions: the State of the Art LOT Winter School, Tilburg 2008 Kees van Deemter Computing Science University of Aberdeen.
Generation of Referring Expressions: the State of the Art LOT Winter School, Tilburg 2008 Kees van Deemter Computing Science University of Aberdeen.
Generation of Referring Expressions: the State of the Art SELLC Winter School, Guangzhou 2010 Kees van Deemter Computing Science University of Aberdeen.
Overspecified reference in hierarchical domains: measuring the benefits for readers Ivandre Paraboni * Judith Masthoff # Kees van Deemter # * = University.
Microplanning (Sentence planning) Part 1 Kees van Deemter.
Corpora in grammatical studies
Ciara R. Wigham, 15 Dec Initiation 1. simple (elementary) 2. complex (episodic, instalment, provisional, dummy, proxy) Refashioning 1. request.
Semantics and Context in Natural Language Processing (NLP) Ari Rappoport The Hebrew University.
CS4018 Formal Models of Computation weeks Computability and Complexity Kees van Deemter (partly based on lecture notes by Dirk Nikodem)
Lecture 3: Salience and Relations Reading: Krahmer and Theune (2002), in Van Deemter and Kibble (Eds.) “Information Sharing: Reference and Presupposition.
Kaplan’s Theory of Indexicals
Language Use and Understanding BCS 261 LIN 241 PSY 261 CLASS 12: BRANIGAN ET AL.: PRIMING.
Dr. Ehud Reiter, Computing Science, University of Aberdeen1 NLG Shared Tasks: Lets try it and see what happens Ehud Reiter (Univ of Aberdeen)
December 2003CSA3050: Natural Language Generation 1 What is Natural Language Generation? When is NLG an Appropriate Technology? NLG System Architectures.
Generation of Referring Expressions: the State of the Art LOT Winter School, Tilburg 2008 Kees van Deemter Computing Science University of Aberdeen.
Discourse Martin Hassel KTH NADA Royal Institute of Technology Stockholm
Albert Gatt LIN1180 – Semantics Lecture 10. Part 1 (from last week) Theories of presupposition: the semantics- pragmatics interface.
 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Discourse and Dialogue.
PSY 369: Psycholinguistics Some basic linguistic theory part3.
PRAGMATICS. 3- Pragmatics is the study of how more gets communicated than is said. It explores how a great deal of what is unsaid is recognized. 4.
Robert's Drawers (and other variations on GRE shared tasks) Gatt, Belz, Reiter, Viethen.
PSY 369: Psycholinguistics Language Production & Comprehension: Conversation & Dialog.
Introduction to Natural Language Generation
LIN1180/LIN5082 Semantics Lecture 3
McEnery, T., Xiao, R. and Y.Tono Corpus-based language studies. Routledge. Unit A 2. Representativeness, balance and sampling (pp13-21)
Linguistics, Pragmatics & Natural Grammar
Lecture 12: 22/6/1435 Natural language processing Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
ASPECTS OF LINGUISTIC COMPETENCE 4 SEPT 09, 2013 – DAY 6 Brain & Language LING NSCI Harry Howard Tulane University.
Albert Gatt LIN1180 Semantics. In this lecture More on the concept of truth A priori / necessary / analytic Presupposition.
Incorporating Extra-linguistic Information into Reference Resolution in Collaborative Task Dialogue Ryu Iida Shumpei Kobayashi Takenobu Tokunaga Tokyo.
THE BIG PICTURE Basic Assumptions Linguistics is the empirical science that studies language (or linguistic behavior) Linguistics proposes theories (models)
Chapter 6. Semantics is the study of the meaning of words, phrases and sentences. In semantic analysis, there is always an attempt to focus on what the.
A system for generating teaching initiatives in a computer-aided language learning dialogue Nanda Slabbers University of Twente Netherlands June 9, 2005.
Breathing and speech planning in turn-taking Francisco Torreira Sara Bögels Stephen Levinson Max Planck Institute for Psycholinguistics Nijmegen, The Netherlands.
1 LIN 1310B Introduction to Linguistics Prof: Nikolay Slavkov TA: Qinghua Tang CLASS 24, April 3, 2007.
RANLP, Borovets Sept Evaluating Algorithms for GRE (Going beyond Toy Domains) Ielka van der Sluis Albert Gatt Kees van Deemter University of.
Generation of Referring Expressions (GRE) The Incremental Algorithm Dale & Reiter (1995)
For Wednesday Read chapter 23 Homework: –Chapter 22, exercises 1,4, 7, and 14.
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
HYMES (1964) He developed the concept that culture, language and social context are clearly interrelated and strongly rejected the idea of viewing language.
Introduction to Dialogue Systems. User Input System Output ?
LECTURE 2: SEMANTICS IN LINGUISTICS
Introduction to Computational Linguistics
Rules, Movement, Ambiguity
Ameeta Agrawal Nikolay Yakovets 01 Dec …Prime Minister Vladimir V. Putin, the country's paramount leader, cut short a trip to Siberia, returning.
The meaning of Language Chapter 5 Semantics and Pragmatics Week10 Nov.19 th -23 rd.
Introduction Chapter 1 Foundations of statistical natural language processing.
Corpus-based evaluation of Referring Expression Generation Albert Gatt Ielka van der Sluis Kees van Deemter Department of Computing Science University.
Topic and the Representation of Discourse Content
Chapter 8. Situated Dialogue Processing for Human-Robot Interaction in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans Sabaleuski.
NATURAL LANGUAGE PROCESSING
Kees van Deemter Generation of Referring Expressions: a crash course Background information and Project HIT 2010.
PHILOSOPHY OF LANGUAGE Some topics and historical issues of the 20 th century.
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
2. The standards of textuality: cohesion Traditional approach to the study of lannguage: sentence as conventional object of study Structuralism (Bloofield,
PRESUPPOSITION PRESENTED BY: SUHAEMI.
Language, Logic, and Meaning
Kees van Deemter Computing Science University of Aberdeen
Generation of Referring Expressions (GRE)
Presentation transcript:

Generation of Referring Expressions: the State of the Art SELLC Winter School, Guangzhou 2010 Kees van Deemter Computing Science University of Aberdeen Guangzhou, Dec 2010

Open Questions in GRE Guangzhou, Dec 2010

Open Questions in GRE Your input is welcome! suggestions about other open questions? ideas about answering them Guangzhou, Dec 2010

OQ1: Reference in context How can existing GRE algorithms be adapted to produce appropriate references in a (discourse or) dialogue context? Much work exists on the choice between broad categories, e.g., pronoun vs. full NP vs demonstrative (Poesio et al; Piwek). This does not help to decide what NP to choose. Integration with GRE is needed. Pioneering accounts are available (Krahmer & Theune 2002, Siddharthan & Copestake 2004, Stoia et al 2007), but these are tentative and largely untested. Dialogue requires modelling of interaction between speaker and hearer (e.g., alignment and collaboration) Guangzhou, Dec 2010

OQ2 Issues regarding knowledge and belief How should mismatches in knowledge between Speaker and Hearer be modelled? GRE so far has kept epistemic operators implicit: all the information in the crucial part of the KB was shared. What if S and H differ? Guangzhou, Dec 2010

OQ2 Issues regarding mutual knowledge Two instances of this problem 1. Litmans airport scenario: What do you say to someone who needs to pick up a person from an airport? (Speaker does not know who the distractors are.) 2. Roman Kutlaks reference to famous people scenario: Someone asks Who is Chu Enlai?, or Who is Nelson Mandela? What should you say? (Who are the distractors? What is their salience?) Guangzhou, Dec 2010

Relevant to the simplifications made by current GRE algorithms. E.g.: The king of France (Frege/Russell/Strawson) Whoever it will be, the winner of this years Tour de France will be less proud than last years winner The winner of the lottery may win 20 million X believes that a witch...; Y believes that she.... (Geach? Groenendijk, Stokhof?) The man with the martini is the murderer, when its actually a soft drink (Donnellan) The ham sandwich is getting restless, by waitress who doesnt know customers name (Nunberg) Guangzhou, Dec 2010

More radical new departures needed? Consider texts about genuinely complex domains: We examine the problem of generating definite noun phrases that are appropriate referring expressions (Opening sentence of the abstract of D&R 1995.) Bushs Middle-East policies are a disaster. Even his closest aids have started to withdraw their support What do these NPs refer to? Is it realistic to want to generate them from a shared KB? Guangzhou, Dec 2010

OQ3: Incrementality Studies of the TUNA corpus suggest that incremental GRE can work very well but only if you have a good preference order How can good preference orders be found? Does every new domain require new empirical studies? Or are there general principles that underlie preference orders? (E.g., frequency or complexity of a property) Sometimes the extremity/unusualness of the values is more important than the attribute itself (cf. Hermann & Deutsch; Aberdeen Cameras study.) Psycholinguistic issue: Relation with realisation order? (Sedivy et al. 1999) Guangzhou, Dec 2010

OQ4: Hearer-oriented GRE Most work on reference in GRE has focussed on production. Exceptions: Paraboni et al. (2007). Preliminary study in first STEC (Belz & Gatt 2007). Khan et al How might one build generators that optimise for the hearer? (High processing speed, low likelihood of errors) And what if it turns out that speakers are bad at this? The egocentricity debate If its practical GRE youre interested in then this allows GRE programs to do better than human speakers. Guangzhou, Dec 2010

OQ5 Multimodality How does textual GRE interact with non-linguistic issues, such as speech (e.g. pitch accent on given information; other prosodic issues; cf. Theunes thesis) pointing (e.g. Van der Sluis & Krahmer [to appear]) salience as determined by physical proximity (as well as textual recency, intrinsic importance of objects, etc.) facial expressions such as gaze, eyebrow movements. These and other issues to be explored in Krahmers VICI project on GRE (Tilburg, ). Guangzhou, Dec 2010

OQ6 Realisation & Lexical Choice Much of what we discussed focusses on Content Determination But referring expressions require words and syntactic constructions as well! But surface phenomena can be difficult and interesting too Gatts exploration of lexical coherence Siddharthans work on lexical ambiguity Imtiaz Khans work on syntactic ambiguity Guangzhou, Dec 2010

OQ6 Realisation & Lexical Choice Siddharthan & Copestake (2004) observed: words can introduce ambiguities. E.g. The old president = the previous present, or the president who is old (i.e., aged) Khan: Syntax can be ambiguous as well: the man on the hill with the telescope the old men and women Guangzhou, Dec 2010

OQ6 Realisation & Lexical Choice One possible position: avoid all ambiguities. Khan: ambiguous strings are not only often generated, but sometimes also preferred by hearers the old men and women preferred over the old men and the old women Finding: surface ambiguities are balanced against other issues (e.g. brevity) Guangzhou, Dec 2010

OQ7 Reference in spacial domains There is preliminary work (e.g. by Gatt), based on simple domains What happens when you want to refer to an area of a country? Ross Turners PhD project (Aberdeen) Input: a set of points in Scotland where ice is predicted to hamper road traffic Example output: icy patches are expected in the North East and on high grounds Guangzhou, Dec 2010

OQ7 Reference in spacial domains Ross Turners PhD project (Aberdeen) Input: a set of points in Scotland where ice is predicted to hamper road traffic. (Each point is on a road.) Example output: Icy patches are expected in the North East and on high grounds This is GRE... but with a twist : it may not be necessary to include all target points it may not be necessary to exclude all other points Referential success becomes a graded affair! Guangzhou, Dec 2010

OQ8 Integration with the rest of NLG GRE is arguably the most mature area of NLG: Linguistic Realisation is the main other contender most GRE practitioners use the same assumptions the fact that the first NLG STEC focused on GRE confirms this Ultimately, the GRE problem is linguistically complete: if we had a flawless GRE algorithm then this algorithm could easily be transformed into an equally flawless algorithm for all of NLG... Guangzhou, Dec 2010

OQ8 Integration with the rest of NLG For example, John walks [S] (The person who) walks [ref NP] Or A man saw a girl with earrings [S] (The man who) saw a girl with earrings [ref NP] Or Someone saw a beautiful girl with incredibly elaborate jade earrings bought in Paris (...) [S] (The person who) saw a beautiful girl with incredibly elaborate jade earrings bought in Paris (...) [ref NP] Guangzhou, Dec 2010

OQ9: Integration between GRE and other areas of linguistics Integration with psycholinguistics: (NLG more generally: G.Kempen et al, A.Roelofs et al. Recent book by M.Guhe.) GRE: modest beginnings in Dale & Reiter 1995 (inspiration from Levelts book) CogSci 2009 workshop Bridging the gap between computational and psycholinguistic approaches to references Special Issue of the journal TopiCS. Guangzhou, Dec 2010

OQ10: Integration between GRE and other areas of linguistics Integration with syntax has so far been meagre interleaving of Linguistic Realisation and Content Determination (Stone & Webber 1998; Krahmer & Theune 2002) Guangzhou, Dec 2010

OQ10: Integration between GRE and other areas of linguistics Integration with formal semantics and pragmatics has been limited DeVault & Stone 2004 on vagueness (based on Kyburg & Morreau 2000) Use of salience (mainly for category choice; see also Krahmer & Theune 2002) Formal semantics focusses on intensionality and quantification Generating appropriate REs in belief contexts: (John knows that the nuclear button / the leftmost button / the red button is dangerous) Guangzhou, Dec 2010

OQ10: Integration between GRE and other areas of linguistics It would be interesting to let GRE explore core areas of formal semantics, e.g. Use a flat KB as input (just like in GRE), to generate quantified NPs like Five rats died, A few rats died, Not all rats died. Find principles for choosing the quantifier pattern thats most appropriate in the utterance situation Early attempts by N.Creaney (2002), but limited progress so far. Guangzhou, Dec 2010

Q11: Problematic referents the water in this pond water 5, 2+3 virtue, power Guangzhou, Dec 2010

Plenty of challenges for enthusiastic young researchers! Guangzhou, Dec 2010