Perceptions of Alignment and Personality in Generated Dialogue

Alastair J. Gill, Carsten Brockmann, Jon Oberlander

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

Abstract

Variation in language style can lead to different perceptions of the interaction, and different behaviour outcomes. Using the CrAg 2 language generation system we examine how accurately judges can perceive character personality from short, automatically generated dialogues, and how alignment (similarity between speakers) alters judge perceptions of the characters' relationship. Whilst personality perception of our dialogues is consistent with perceptions of human behaviour, we find that the introduction of alignment leads to negative perceptions of the dialogues and the inter-locutors' relationship. A follow up evaluation study of the perceptions of different forms of alignment in the dialogues reveals that while similarity at polarity, topic and construction levels is viewed positively, similarity at the word level is regarded negatively. We discuss our findings in relation to the literature and in the context of dialogue systems.
Original languageEnglish
Title of host publicationProceedings of the Seventh International Natural Language Generation Conference
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages40-48
Number of pages9
Publication statusPublished - 2012

Publication series

NameINLG '12
PublisherAssociation for Computational Linguistics

Fingerprint

Dive into the research topics of 'Perceptions of Alignment and Personality in Generated Dialogue'. Together they form a unique fingerprint.

Cite this