Adversarial Learning on the Latent Space for Diverse Dialog Generation
Kashif Khan, Gaurav Sahu, Vikash Balasubramanian, Lili Mou, Olga Vechtomova
Abstract
Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation, but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework based on generative adversarial nets for generating conditioned responses. Our model first learns a meaningful representation of sentences by autoencoding, and then learns to map an input query to the response representation, which is in turn decoded as a response sentence. Both quantitative and qualitative evaluations show that our model generates more fluent, relevant, and diverse responses than existing state-of-the-art methods.
BibTeX
@inproceedings{khan-etal-2020-adversarial,
title = "Adversarial Learning on the Latent Space for Diverse Dialog Generation",
author = "Khan, Kashif and
Sahu, Gaurav and
Balasubramanian, Vikash and
Mou, Lili and
Vechtomova, Olga",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.441/",
doi = "10.18653/v1/2020.coling-main.441",
pages = "5026--5034"
}