A Compare Aggregate Transformer for Understanding Document-grounded Dialogue

Abstract

Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue history that is not related to the current dialogue may introduce noise in the KS processing. In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation. We designed two different comparison mechanisms to reduce noise (before and during decoding). In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap. Experimental results on the CMUDoG dataset show that the proposed CAT model outperforms the state-of-the-art approach and strong baselines.

arXiv comment7pages, 3 figures, 6 tables, Findings of EMNLP 2020

References in corpus (6)

• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Bidirectional Attention Flow for Machine Comprehension
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation