Affect-LM: a Neural Language Model for Customizable Affective Text Generation

Ghosh, S., Chollet, M. , Laksana, E., Morency, L.-P. and Scherer, S. (2017) Affect-LM: a Neural Language Model for Customizable Affective Text Generation. In: 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017), Vancouver, BC, Canada, 30 Jul - 04 Aug 2017, pp. 634-642. ISBN 9781945626753 (doi: 10.18653/v1/P17-1059)

Full text not currently available from Enlighten.

Publisher's URL: https://doi.org/10.18653/v1/P17-1059

Abstract

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research effort in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generation of conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM can generate naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Chollet, Dr Mathieu
Authors: Ghosh, S., Chollet, M., Laksana, E., Morency, L.-P., and Scherer, S.
College/School:College of Science and Engineering > School of Computing Science
ISBN:9781945626753

University Staff: Request a correction | Enlighten Editors: Update this record