Empirical Methods in Natural Language Generation: Data-oriented Methods and Empirical Evaluation

✍ Scribed by Regina Barzilay (auth.), Emiel Krahmer, Mariët Theune (eds.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 2010
• Tongue: English
• Leaves: 362
• Series: Lecture Notes in Computer Science 5790 : Lecture Notes in Artificial Intelligence
• Edition: 1
• Category: Library

✦ Synopsis

Natural language generation (NLG) is a subfield of natural language processing (NLP) that is often characterized as the study of automatically converting non-linguistic representations (e.g., from databases or other knowledge sources) into coherent natural language text. In recent years the field has evolved substantially. Perhaps the most important new development is the current emphasis on data-oriented methods and empirical evaluation. Progress in related areas such as machine translation, dialogue system design and automatic text summarization and the resulting awareness of the importance of language generation, the increasing availability of suitable corpora in recent years, and the organization of shared tasks for NLG, where different teams of researchers develop and evaluate their algorithms on a shared, held out data set have had a considerable impact on the field, and this book offers the first comprehensive overview of recent empirically oriented NLG research.

✦ Table of Contents

Front Matter....Pages -
Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation....Pages 1-12
Spanning Tree Approaches for Statistical Sentence Generation....Pages 13-44
On the Limits of Sentence Compression by Deletion....Pages 45-66
Learning Adaptive Referring Expression Generation Policies for Spoken Dialogue Systems....Pages 67-84
Modelling and Evaluation of Lexical and Syntactic Alignment with a Priming-Based Microplanner....Pages 85-104
Natural Language Generation as Planning under Uncertainty for Spoken Dialogue Systems....Pages 105-120
Generating Approximate Geographic Descriptions....Pages 121-140
A Flexible Approach to Class-Based Ordering of Prenominal Modifiers....Pages 141-162
Attribute-Centric Referring Expression Generation....Pages 163-179
Assessing the Trade-Off between System Building Cost and Output Quality in Data-to-Text Generation....Pages 180-200
Human Evaluation of a German Surface Realisation Ranker....Pages 201-221
Structural Features for Predicting the Linguistic Quality of Text....Pages 222-241
Towards Empirical Evaluation of Affective Tactical NLG....Pages 242-263
Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges....Pages 264-293
Generating Referring Expressions in Context: The GREC Task Evaluation Challenges....Pages 294-327
The First Challenge on Generating Instructions in Virtual Environments....Pages 328-352
Back Matter....Pages -

✦ Subjects

Artificial Intelligence (incl. Robotics); Information Storage and Retrieval; Information Systems Applications (incl.Internet); Database Management; Data Mining and Knowledge Discovery; Multimedia Information Systems