Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks

Kim, Jintae; Oh, Shinhyeok; Kwon, Oh-Woog; Kim, Harksoo

doi:10.3390/app9183908

Open AccessArticle

Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks

¹

Program of Computer and Communications Engineering, Kangwon National University, Chuncheon 24341, Korea

²

Electronics and Telecommunications Research Institute, Daejeon 34129, Korea

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2019, 9(18), 3908; https://doi.org/10.3390/app9183908

Submission received: 20 August 2019 / Revised: 13 September 2019 / Accepted: 16 September 2019 / Published: 18 September 2019

(This article belongs to the Special Issue Natural Language Processing: Emerging Neural Approaches and Applications)

Download

Browse Figure

Versions Notes

Abstract

To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without considering contextual importance. To mitigate this problem, we propose a multi-turn chatbot model in which previous utterances participate in response generation using different weights. The proposed model calculates the contextual importance of previous utterances by using an attention mechanism. In addition, we propose a training method that uses two types of Wasserstein generative adversarial networks to improve the quality of responses. In experiments with the DailyDialog dataset, the proposed model outperformed the previous state-of-the-art models based on various performance measures.

Keywords: multi-turn chatbot; dialogue context encoding; WGAN-based response generation

Share and Cite

MDPI and ACS Style

Kim, J.; Oh, S.; Kwon, O.-W.; Kim, H. Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks. Appl. Sci. 2019, 9, 3908. https://doi.org/10.3390/app9183908

AMA Style

Kim J, Oh S, Kwon O-W, Kim H. Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks. Applied Sciences. 2019; 9(18):3908. https://doi.org/10.3390/app9183908

Chicago/Turabian Style

Kim, Jintae, Shinhyeok Oh, Oh-Woog Kwon, and Harksoo Kim. 2019. "Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks" Applied Sciences 9, no. 18: 3908. https://doi.org/10.3390/app9183908

APA Style

Kim, J., Oh, S., Kwon, O.-W., & Kim, H. (2019). Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks. Applied Sciences, 9(18), 3908. https://doi.org/10.3390/app9183908

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI