Paper: Perceptions of Alignment and Personality in Generated Dialogue

ACL ID W12-1508
Title Perceptions of Alignment and Personality in Generated Dialogue
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2012
Authors

Variation in language style can lead to differ- ent perceptions of the interaction, and differ- ent behaviour outcomes. Using the CRAG 2 language generation system we examine how accurately judges can perceive character per- sonality from short, automatically generated dialogues, and how alignment (similarity be- tween speakers) alters judge perceptions of the characters? relationship. Whilst personality perception of our dialogues is consistent with perceptions of human behaviour, we find that