20 September 2007
Generating Language with Personality
Room M308, Maths and Computing
12:30 - 1:45
François Mairesse of the University of Sheffield
Over the last fifty years, the "Big Five" model of personality traits has become a standard in psychology, and research has systematically documented correlations between a wide range of linguistic variables and the Big Five traits. A distinct line of research has explored methods for automatically generating language that varies along personality dimensions.
We present PERSONAGE (PERSONAlity GEnerator), the first highly parametrizable language generator for extraversion, the most important dimension of personality. We evaluate two personality generation methods: (1) direct generation with particular parameter settings suggested by the psychology literature; and (2) overgeneration and selection using statistical models trained from judge's ratings.
Results show that both methods reliably generate utterances that vary along the extraversion dimension, according to human judges. We also report results for other personality dimensions, with the aim to produce language expressing any combination of personality traits.
Save to your Calendar
Contact: Short Biography:
François Mairesse is completing his PhD thesis on linguistic variation in natural language generation at the University of Sheffield, under the supervision of Marilyn Walker. His main interest is in modeling individual differences in language, using both data-driven and psychologically motivated approaches.
The talk is an extended version of a presentation given at this year's ACL conference in Prague.