SEGUE: A Hybrid Case-Based Surface Natural Language Generator

SEGUE: A Hybrid Case-Based Surface Natural Language Generator

This paper presents Segue, a hybrid surface natural language generator that employs case-based paradigm but performs rule-based adaptations. It uses an annotated corpus as its knowledge source and employs grammatical rules to construct new sentences. By using adaptation-guided retrieval to select ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pan, Shimei, Shaw, James
Format: Buchkapitel
Sprache:eng
Schlagworte:
Annotate Corpus
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Exact sciences and technology
Grammatical Rule
Insertion Operator
Machine Translation
Retrieval Phase
Speech and sound recognition and synthesis. Linguistics
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents Segue, a hybrid surface natural language generator that employs case-based paradigm but performs rule-based adaptations. It uses an annotated corpus as its knowledge source and employs grammatical rules to construct new sentences. By using adaptation-guided retrieval to select cases that can be adapted easily to the desired output, Segue simplifies the process and avoids generating ungrammatical sentences. The evaluation results show the system generates grammatically correct sentences (91%), but disfluency is still an issue.
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-27823-8_14