Natural Language Generation: Third International Conference, INLG 2004, Brockenhurst, UK, July 14-16, 2004, Proceedings (Lecture Notes in Computer Science)

The Third International Conference On Natural Language Generation (inlg 2004) Was Held From 14th To 16th July 2004 At Careys Manor, Brockenhurst, Uk. Supported By The Association For Computational Linguistics Special - Terest Group On Generation, The Conference Continued A Twenty-year Tradition Of Biennial International Meetings On Research Into Natural Language Generation. Recent Conference Venues Have Included Mitzpe Ramon, Israel (inlg 2000) And New York, Usa (inlg 2002). It Was Our Pleasure To Invite The Thriving And Friendly Nlg Research Community To The Beautiful New Forest In The South Of England For Inlg 2004. Inlg Is The Leading International Conference In The ?eld Of Natural Language Generation. It Provides A Forum For The Presentation And Discussion Of Original Research On All Aspects Of The Generation Of Language, Including Psychological Modelling Of Human Language Production As Well As Computational Approaches To The Automatic Generation Of Language. This Volume Includes A Paper By The Keynote Speaker, Ardi Roelofs Of The Max Planck Institute For Psycholingu- Tics And The F. C. Donders Centre For Cognitiveneuroimaging,18 Regular Papers Reportingthelatestresearchresultsanddirections,and4studentpapersdescr- Ing Doctoral Work In Progress. These Papers Reveal A Particular Concentration Of Current Research E?ort On Statistical And Machine Learning Methods, On Referring Expressions, And On Variation In Surface Realisation. The Papers Were Selected From 46 Submissions From All Over The World (27 From Europe, 13 From North America, 6 From Elsewhere), Which Were Subjected To A Rigorous Double-blind Reviewing Process Undertaken By Our Hard-working Programme Committee. Keynote Paper -- The Seduced Speaker: Modeling Of Cognitive Control -- Regular Papers -- Generating Intensional Answers In Intelligent Question Answering Systems -- Salience-driven Text Planning -- Finetuning Nlg Through Experiments With Human Subjects: The Case Of Vague Descriptions -- Indirect Supervised Learning Of Content Selection Logic -- Generating Referring Expressions Using Perceptual Groups -- The Use Of A Structural N-gram Language Model In Generation-heavy Hybrid Machine Translation -- On Referring To Sets Of Objects Naturally -- An Atms Approach To Systemic Sentence Generation -- A Corpus-based Methodology For Evaluating Metrics Of Coherence For Text Structuring -- Classification-based Generation Using Tag -- Resolving Structural Ambiguity In Generated Speech -- A Framework For Stylistically Controlled Generation -- Segue: A Hybrid Case-based Surface Natural Language Generator -- Modelling Politeness In Natural Language Generation -- Context-based Incremental Generation For Dialogue -- Contextual Influences On Near-synonym Choice -- Overgenerating Referring Expressions Involving Relations And Booleans -- Reining In Ccg Chart Realization -- Student Papers -- Categorization Of Narrative Semantics For Use In Generative Multidocument Summarization -- Corpus-based Planning Of Deictic Gestures In Comic -- Hybrid Nlg In A Generic Dialog System -- Two Kinds Of Alternative Sets And A Marking Principle – When To Say Also. Anja Belz, Roger Evans, Paul Piwek (eds.). Also Issued Online. Front Matter....Pages - The Seduced Speaker: Modeling of Cognitive Control....Pages 1-10 Generating Intensional Answers in Intelligent Question Answering Systems....Pages 11-20 Salience-Driven Text Planning....Pages 21-30 Finetuning NLG Through Experiments with Human Subjects: The Case of Vague Descriptions....Pages 31-40 Indirect Supervised Learning of Content Selection Logic....Pages 41-50 Generating Referring Expressions Using Perceptual Groups....Pages 51-60 The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation....Pages 61-69 On Referring to Sets of Objects Naturally....Pages 70-79 An ATMS Approach to Systemic Sentence Generation....Pages 80-89 A Corpus-Based Methodology for Evaluating Metrics of Coherence for Text Structuring....Pages 90-99 Classification-Based Generation Using TAG....Pages 100-109 Resolving Structural Ambiguity in Generated Speech....Pages 110-119 A Framework for Stylistically Controlled Generation....Pages 120-129 SEGUE: A Hybrid Case-Based Surface Natural Language Generator....Pages 130-140 Modelling Politeness in Natural Language Generation....Pages 141-150 Context-Based Incremental Generation for Dialogue....Pages 151-160 Contextual Influences on Near-Synonym Choice....Pages 161-170 Overgenerating Referring Expressions Involving Relations and Booleans....Pages 171-181 Reining in CCG Chart Realization....Pages 182-191 Categorization of Narrative Semantics for Use in Generative Multidocument Summarization....Pages 192-197 Corpus-Based Planning of Deictic Gestures in COMIC....Pages 198-204 Hybrid NLG in a Generic Dialog System....Pages 205-211 Two Kinds of Alternative Sets and a Marking Principle – When to Say Also ....Pages 212-218 Back Matter....Pages - The Third International Conference on Natural Language Generation (INLG 2004) was held from 14th to 16th July 2004 at Careys Manor, Brockenhurst, UK. Supported by the Association for Computational Linguistics Special - terest Group on Generation, the conference continued a twenty-year tradition of biennial international meetings on research into natural language generation. Recent conference venues have included Mitzpe Ramon, Israel (INLG 2000) and New York, USA (INLG 2002). It was our pleasure to invite the thriving and friendly NLG research community to the beautiful New Forest in the south of England for INLG 2004. INLG is the leading international conference in the?eld of natural language generation. It provides a forum for the presentation and discussion of original research on all aspects of the generation of language, including psychological modelling of human language production as well as computational approaches to the automatic generation of language. This volume includes a paper by the keynote speaker, Ardi Roelofs of the Max Planck Institute for Psycholingu- tics and the F.C. Donders Centre for CognitiveNeuroimaging,18 regular papers reportingthelatestresearchresultsanddirections, and4studentpapersdescr- ing doctoral work in progress. These papers reveal a particular concentration of current research e?ort on statistical and machine learning methods, on referring expressions, and on variation in surface realisation. The papers were selected from 46 submissions from all over the world (27 from Europe, 13 from North America, 6 from elsewhere), which were subjected to a rigorous double-blind reviewing process undertaken by our hard-working programme committee The third edition of this long-serving successful reference work is a 'must-have' reference for anyone needing or desiring an understanding of the structure, chemistry, properties, production and uses of starches and their derivatives.

* Includes specific information on corn, wheat, potato, rice, and new chapters on rye, oat and barley (including waxy barley) starches

* Covers the isolation processes, properties, functionalities, and uses of the most commonly used starches.

* Explores the genetics, biochemistry, and physical structure of starches

* Presents current and emerging application trends for starch

This book constitutes the refereed proceedings of the Third International Conference on Natural Language Generation, INLG 2004, held in Brockenhurst, UK in July 2004. The 18 revised full papers presented together with an invited keynote paper and 4 student papers reporting ongoing PhD research work were carefully reviewed and selected from 46 submissions. All current aspects of the generation of natural language are addressed, including psychological modeling of human language production as well as computational approaches to the automatic generation of language The third edition of this long-serving successful reference work is a 'must-have' reference for anyone needing or desiring an understanding of the structure, chemistry, properties, production and uses of starches and their derivatives. * Everything needed to evaluate and apply the appropriate starch-based solution * Explores the genetics, biochemistry, and physical structure of starches * Includes specific information on corn, wheat, potato, rice, rye, oat and barley-based starches * Presents new application trends for starch Unlike most Natural Language Generation programs that run on serial, digital computers, human speakers are occasionally distracted while performing a natural language generation task.