End-to-end Conversation Modeling Track in DSTC6

TL;DR

This paper introduces a challenge track in DSTC6 focused on training end-to-end neural conversation models using human-to-human dialog data to improve naturalness and informativeness in diverse dialog tasks.

Contribution

It proposes a new challenge track for DSTC6 that emphasizes end-to-end training of dialog systems with human conversation data across various tasks.

Findings

Developed a benchmark for end-to-end dialog modeling.

Evaluated models on multiple dialog tasks.

Enhanced naturalness and informativeness of system responses.

Abstract

End-to-end training of neural networks is a promising approach to automatic construction of dialog systems using a human-to-human dialog corpus. Recently, Vinyals et al. tested neural conversation models using OpenSubtitles. Lowe et al. released the Ubuntu Dialogue Corpus for researching unstructured multi-turn dialogue systems. Furthermore, the approach has been extended to accomplish task oriented dialogs to provide information properly with natural conversation. For example, Ghazvininejad et al. proposed a knowledge grounded neural conversation model [3], where the research is aiming at combining conversational dialogs with task-oriented knowledge using unstructured data such as Twitter data for conversation and Foursquare data for external knowledge.However, the task is still limited to a restaurant information service, and has not yet been tested with a wide variety of dialog tasks. In addition, it is still unclear how to create intelligent dialog systems that can respond like a human agent. In consideration of these problems, we proposed a challenge track to the 6th dialog system technology challenges (DSTC6) using human-to-human dialog data to mimic human dialog behaviors. The focus of the challenge track is to train end-to-end conversation models from human-to-human conversation and accomplish end-to-end dialog tasks in various situations assuming a customer service, in which a system plays a role of human agent and generates natural and informative sentences in response to user's questions or comments given dialog context.