Empirical Methods in Natural Language Generation

1. Front Matter

   PDF

2. Text-to-Text Generation

   1. Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation

      • Regina Barzilay

      Pages 1-12

   2. Spanning Tree Approaches for Statistical Sentence Generation

      • Stephen Wan, Mark Dras, Robert Dale, Cécile Paris

      Pages 13-44

   3. On the Limits of Sentence Compression by Deletion

      • Erwin Marsi, Emiel Krahmer, Iris Hendrickx, Walter Daelemans

      Pages 45-66

3. NLG in Interaction

   1. Learning Adaptive Referring Expression Generation Policies for Spoken Dialogue Systems

      • Srinivasan Janarthanam, Oliver Lemon

      Pages 67-84

   2. Modelling and Evaluation of Lexical and Syntactic Alignment with a Priming-Based Microplanner

      • Hendrik Buschmeier, Kirsten Bergmann, Stefan Kopp

      Pages 85-104

   3. Natural Language Generation as Planning under Uncertainty for Spoken Dialogue Systems

      • Verena Rieser, Oliver Lemon

      Pages 105-120

4. Referring Expression Generation

   1. Generating Approximate Geographic Descriptions

      • Ross Turner, Somayajulu Sripada, Ehud Reiter

      Pages 121-140

   2. A Flexible Approach to Class-Based Ordering of Prenominal Modifiers

      • Margaret Mitchell

      Pages 141-162

   3. Attribute-Centric Referring Expression Generation

      • Robert Dale, Jette Viethen

      Pages 163-179

5. Evaluation of NLG

   1. Assessing the Trade-Off between System Building Cost and Output Quality in Data-to-Text Generation

      • Anja Belz, Eric Kow

      Pages 180-200

   2. Human Evaluation of a German Surface Realisation Ranker

      • Aoife Cahill, Martin Forst

      Pages 201-221

   3. Structural Features for Predicting the Linguistic Quality of Text

      • Ani Nenkova, Jieun Chae, Annie Louis, Emily Pitler

      Pages 222-241

   4. Towards Empirical Evaluation of Affective Tactical NLG

      • Ielka van der Sluis, Chris Mellish

      Pages 242-263

6. Shared Task Challenges for NLG

   1. Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges

      • Albert Gatt, Anja Belz

      Pages 264-293

   2. Generating Referring Expressions in Context: The GREC Task Evaluation Challenges

      • Anja Belz, Eric Kow, Jette Viethen, Albert Gatt

      Pages 294-327

   3. The First Challenge on Generating Instructions in Virtual Environments

      • Alexander Koller, Kristina Striegnitz, Donna Byron, Justine Cassell, Robert Dale, Johanna Moore et al.

      Pages 328-352

7. Back Matter

   PDF

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.

• automatic translation
• human-human communication
• information extraction
• information retrieval
• knowledge
• learning
• modeling
• natural language
• speech recognition
• text summarization

• Faculty of Humanities, Department of Communication and Information Sciences (DCI), Tilburg University, Tilburg, The Netherlands

  Emiel Krahmer

• Human Media Interaction (HMI), Department of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, Enschede, The Netherlands

  Mariët Theune

Policies and ethics