Flexible natural language generation in multiple contexts

Caroline Cullen, Ian O'Neill, Philip Hanna

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)
257 Downloads (Pure)

Abstract

We present a practical approach to Natural Language Generation (NLG) for spoken dialogue systems. The approach is based on small template fragments (mini-templates). The system’s object architecture facilitates generation of phrases across pre-defined business domains and registers, as well as into different languages. The architecture simplifies NLG in well-understood application contexts, while providing the flexibility for a developer and for the system, to vary linguistic output according to dialogue context, including any intended affective impact. Mini-templates are used with a suite of domain term objects, resulting in an NLG system (MINTGEN – MINi-Template GENerator) whose extensibility and ease of maintenance is enhanced by the sparsity of information devoted to individual domains. The system also avoids the need for specialist linguistic competence on the part of the system maintainer.
Original languageEnglish
Title of host publicationHuman Language Technology. Challenges of the Information Society . Third Language and Technology Conference, LTC 2007: Proceedings (Revised Selected Papers)
PublisherSpringer
Pages142-153
Number of pages12
ISBN (Electronic)9783642042355
ISBN (Print)9783642042348
DOIs
Publication statusPublished - 25 Aug 2009
EventThird Language and Technology Conference, LTC 2007 - Poznan, Poland
Duration: 05 Oct 200707 Oct 2007

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume5603
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
PublisherSpringer
ISSN (Print)2945-9133
ISSN (Electronic)2945-9141

Conference

ConferenceThird Language and Technology Conference, LTC 2007
Country/TerritoryPoland
CityPoznan
Period05/10/200707/10/2007

Fingerprint

Dive into the research topics of 'Flexible natural language generation in multiple contexts'. Together they form a unique fingerprint.

Cite this