Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems

Abstract

The NOESIS II challenge, as the Track 2 of the 8th Dialogue System Technology Challenges (DSTC 8), is the extension of DSTC 7. This track incorporates new elements that are vital for the creation of a deployed task-oriented dialogue system. This paper describes our systems that are evaluated on all subtasks under this challenge. We study the problem of employing pre-trained attention-based network for multi-turn dialogue systems. Meanwhile, several adaptation methods are proposed to adapt the pre-trained language models for multi-turn dialogue systems, in order to keep the intrinsic property of dialogue systems. In the released evaluation results of Track 2 of DSTC 8, our proposed models ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively.

arXiv commentAccepted by AAAI 2020, Workshop on DSTC8

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• An Information Retrieval Approach to Short Text Conversation
• A Large-Scale Corpus for Conversation Disentanglement
• Modeling Multi-turn Conversation with Deep Utterance Aggregation
• The Eighth Dialog System Technology Challenge
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus

Cited by in corpus (2)

• Multi-turn Response Selection using Dialogue Dependency Relations
• Response Selection for Multi-Party Conversations with Dynamic Topic Tracking