Natural language generation : third international conference, INLG 2004, Brockenhurst, UK, July 14-16, 2004 : proceedings

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 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. Table of Contents......Page 10 The Seduced Speaker: Modeling of Cognitive Control......Page 12 Generating Intensional Answers in Intelligent Question Answering Systems......Page 22 Salience-Driven Text Planning......Page 32 Finetuning NLG Through Experiments with Human Subjects: The Case of Vague Descriptions......Page 42 Indirect Supervised Learning of Content Selection Logic......Page 52 Generating Referring Expressions Using Perceptual Groups......Page 62 The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation......Page 72 On Referring to Sets of Objects Naturally......Page 81 An ATMS Approach to Systemic Sentence Generation......Page 91 A Corpus-Based Methodology for Evaluating Metrics of Coherence for Text Structuring......Page 101 Classification-Based Generation Using TAG......Page 111 Resolving Structural Ambiguity in Generated Speech......Page 121 A Framework for Stylistically Controlled Generation......Page 131 SEGUE: A Hybrid Case-Based Surface Natural Language Generator......Page 141 Modelling Politeness in Natural Language Generation......Page 152 Context-Based Incremental Generation for Dialogue......Page 162 Contextual Influences on Near-Synonym Choice......Page 172 Overgenerating Referring Expressions Involving Relations and Booleans......Page 182 Reining in CCG Chart Realization......Page 193 Categorization of Narrative Semantics for Use in Generative Multidocument Summarization......Page 203 Corpus-Based Planning of Deictic Gestures in COMIC......Page 209 Hybrid NLG in a Generic Dialog System......Page 216 Two Kinds of Alternative Sets and a Marking Principle – When to Say Also......Page 223 Author Index......Page 230 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 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