Computing Dialogue Acts from Features with Transformation-Based Learning

Simple item page
dc.creatorSamuel, Ken
dc.creatorCarberry, Sandra
dc.creatorVijay-Shanker, K.
dc.date1998-06-02
dc.date.accessioned2026-07-07T02:36:15Z
dc.date.available2026-07-07T02:36:15Z
dc.descriptionTo interpret natural language at the discourse level, it is very useful to accurately recognize dialogue acts, such as SUGGEST, in identifying speaker intentions. Our research explores the utility of a machine learning method called Transformation-Based Learning (TBL) in computing dialogue acts, because TBL has a number of advantages over alternative approaches for this application. We have identified some extensions to TBL that are necessary in order to address the limitations of the original algorithm and the particular demands of discourse processing. We use a Monte Carlo strategy to increase the applicability of the TBL method, and we select features of utterances that can be used as input to improve the performance of TBL. Our system is currently being tested on the VerbMobil corpora of spoken dialogues, producing promising preliminary results.
dc.description8 pages, 1 Postscript figure, uses aaai.sty and aaai.bst
dc.identifierhttps://arxiv.org/abs/cmp-lg/9806002
dc.identifierhttp://arxiv.org/abs/cmp-lg/9806002
dc.identifierApplying Machine Learning to Discourse Processing: Papers from the 1998 AAAI Spring Symposium
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/15846
dc.subjectComputation and Language
dc.titleComputing Dialogue Acts from Features with Transformation-Based Learning
dc.typetext

Files

Collections

arXiv