Modelling alignment for affective dialogue

Carsten Brockmann, Amy Isard, Jon Oberlander, Michael White

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

Abstract

For a successful and satisfying interaction, a dialogue participant may align their language to be more like that of their interlocutor. In the first part of this paper, we examine the alignment phenomenon from the viewpoint of personalityrelated, linguistic, sociolinguistic and psycholinguistic research, concluding that some people are stronger aligners than others. Motivated by these results, we describe an approach to modelling alignment behaviour in a natural language generation system, using the OpenCCG surface realiser [30], which allows utterance candidates to be ranked by n-gram language models. We investigate the extent to which alignment can be simulated using word sequences alone (not syntactic structures). To this end, we interpolate a default language model with one calculated on the basis of a cached sentence. Experiments on sentences with the prepositional/double object alternation show that varying the weight given to the cache model varies the propensity to align.
Original languageEnglish
Title of host publicationWorkshop on Adapting the Interaction Style to Affective Factors at the 10th International Conference on User Modeling (UM-05)
Number of pages5
Publication statusPublished - 2005

Fingerprint Dive into the research topics of 'Modelling alignment for affective dialogue'. Together they form a unique fingerprint.

Cite this