Adversarial Learning on the Latent Space for Diverse Dialog Generation

9Citations
Citations of this article
67Readers
Mendeley users who have this article in their library.

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.

References Powered by Scopus

Long Short-Term Memory

76925Citations
N/AReaders
Get full text

SWITCHBOARD: Telephone speech corpus for research and development

1519Citations
N/AReaders
Get full text

A diversity-promoting objective function for neural conversation models

1504Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Deep Learning for Dialogue Systems: Chit-Chat and Beyond

14Citations
N/AReaders
Get full text

FPGNN: Fair path graph neural network for mitigating discrimination

11Citations
N/AReaders
Get full text

PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism

2Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Khan, K., Sahu, G., Balasubramanian, V., Mou, L., & Vechtomova, O. (2020). Adversarial Learning on the Latent Space for Diverse Dialog Generation. In COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference (pp. 5026–5034). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.coling-main.441

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 16

73%

Researcher 4

18%

Lecturer / Post doc 2

9%

Readers' Discipline

Tooltip

Computer Science 20

77%

Linguistics 4

15%

Neuroscience 1

4%

Social Sciences 1

4%

Save time finding and organizing research with Mendeley

Sign up for free