Steering Output Style and Topic in Neural Response Generation

Di Wang, Nebojsa Jojic, Chris Brockett, Eric Nyberg


Abstract
We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational systems, where successful agents need to produce language in a specific style and generate responses steered by a human puppeteer or external knowledge. We decompose the neural generation process into empirically easier sub-problems: a faithfulness model and a decoding method based on selective-sampling. We also describe training and sampling algorithms that bias the generation process with a specific language style restriction, or a topic restriction. Human evaluation results show that our proposed methods are able to to restrict style and topic without degrading output quality in conversational tasks.
Anthology ID:
D17-1228
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2140–2150
Language:
URL:
https://www.aclweb.org/anthology/D17-1228
DOI:
10.18653/v1/D17-1228
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1228.pdf
Attachment:
 D17-1228.Attachment.zip