Empirical Methods in Natural Language Generation Data-oriented Methods and Empirical Evaluation /
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 ha...
Συγγραφή απο Οργανισμό/Αρχή: | |
---|---|
Άλλοι συγγραφείς: | , |
Μορφή: | Ηλεκτρονική πηγή Ηλ. βιβλίο |
Γλώσσα: | English |
Έκδοση: |
Berlin, Heidelberg :
Springer Berlin Heidelberg : Imprint: Springer,
2010.
|
Σειρά: | Lecture Notes in Computer Science,
5790 |
Θέματα: | |
Διαθέσιμο Online: | Full Text via HEAL-Link |
Πίνακας περιεχομένων:
- Text-to-Text Generation
- Probabilistic Approaches for Modeling Text Structure and Their Application to Text-to-Text Generation
- Spanning Tree Approaches for Statistical Sentence Generation
- On the Limits of Sentence Compression by Deletion
- NLG in Interaction
- Learning Adaptive Referring Expression Generation Policies for Spoken Dialogue Systems
- Modelling and Evaluation of Lexical and Syntactic Alignment with a Priming-Based Microplanner
- Natural Language Generation as Planning under Uncertainty for Spoken Dialogue Systems
- Referring Expression Generation
- Generating Approximate Geographic Descriptions
- A Flexible Approach to Class-Based Ordering of Prenominal Modifiers
- Attribute-Centric Referring Expression Generation
- Evaluation of NLG
- Assessing the Trade-Off between System Building Cost and Output Quality in Data-to-Text Generation
- Human Evaluation of a German Surface Realisation Ranker
- Structural Features for Predicting the Linguistic Quality of Text
- Towards Empirical Evaluation of Affective Tactical NLG
- Shared Task Challenges for NLG
- Introducing Shared Tasks to NLG: The TUNA Shared Task Evaluation Challenges
- Generating Referring Expressions in Context: The GREC Task Evaluation Challenges
- The First Challenge on Generating Instructions in Virtual Environments.