Skip to Main content Skip to Navigation
Conference papers

Purely Corpus-based Automatic Conversation Authoring

Abstract : This paper presents an automatic corpus-based process to author an open-domain conversational strategy usable both in chatterbot systems and as a fallback strategy for out-of-domain human utterances. Our approach is implemented on a corpus of television drama subtitles. This system is used as a chatterbot system to collect a corpus of 41 open-domain textual dialogues with 27 human participants. The general capabilities of the system are studied through objective measures and subjective self-reports in terms of understandability, repetition and coherence of the system responses selected in reaction to human utterances. Subjective evaluations of the collected dialogues are presented with respect to amusement, engagement and enjoyability. The main factors influencing those dimensions in our chatterbot experiment are discussed.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01309202
Contributor : Guillaume Dubuisson Duplessis <>
Submitted on : Friday, April 29, 2016 - 9:52:24 AM
Last modification on : Wednesday, June 24, 2020 - 2:30:05 PM
Document(s) archivé(s) le : Tuesday, November 15, 2016 - 5:43:36 PM

File

lrec2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01309202, version 1

Citation

Guillaume Dubuisson Duplessis, Vincent Letard, Anne-Laure Ligozat, Sophie Rosset. Purely Corpus-based Automatic Conversation Authoring. 10th edition of the Language Resources and Evaluation Conference (LREC), May 2016, Portorož, Slovenia. pp.ISBN: 978-2-9517408-9-1. ⟨hal-01309202⟩

Share

Metrics

Record views

432

Files downloads

319