SEGUE: A Hybrid Case-Based Surface Natural Language Generator

Files

segueahybride.pdf (250.15 KB)

Links to Files

https://link.springer.com/chapter/10.1007/978-3-540-27823-8_14

Permanent Link

https://doi.org/10.1007/978-3-540-27823-8_14
 http://hdl.handle.net/11603/38621

Collections

UMBC Information Systems Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-5989-8543

Date

2004

Type of Work

conference papers and proceedings
book chapters
postprints
Text

Department

Program

Citation of Original Publication

Pan, Shimei, and James Shaw. “SEGUE: A Hybrid Case-Based Surface Natural Language Generator.” In Natural Language Generation, edited by Anja Belz, Roger Evans, and Paul Piwek, 130–40. Berlin, Heidelberg: Springer, 2004. https://doi.org/10.1007/978-3-540-27823-8_14.

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Annotate Corpus
Insertion Operator
Retrieval Phase
Machine Translation
Grammatical Rule

Abstract

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.