Affective Neural Response Generation
- Nabiha Asghar
- Pascal Poupart, University of Waterloo
- Jesse Hoey
- Xin Jiang
- Lili Mou
Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step in this direction by proposing three novel ways to incorporate affective/emotional aspects into long short term memory (LSTM) encoder-decoder neural conversation models: (1) affective word embeddings, which are cognitively engineered, (2) affect-based objective functions that augment the standard cross-entropy loss, and (3) affectively diverse beam search for decoding. Experiments show that these techniques improve the open-domain conversational prowess of encoder-decoder networks by enabling them to produce more natural and emotionally rich responses.
Citation
N. Asghar, P. Poupart, J. Hoey, X. Jiang, L. Mou. "Affective Neural Response Generation". ECIR, pp 154-166, March 2018.| Keywords: | Dialogue systems, Human computer interaction, Natural language processing, Affective computing |
| Category: | In Conference |
| Web Links: | doi |
| Springer |
BibTeX
@incollection{Asghar+al:ECIR18,
author = {Nabiha Asghar and Pascal Poupart and Jesse Hoey and Xin Jiang and
Lili Mou},
title = {Affective Neural Response Generation},
Pages = {154-166},
booktitle = {},
year = 2018,
}Last Updated: February 03, 2021Submitted by Sabina P
