Improving Background Based Conversation with Context-aware Knowledge Pre-selection
arXiv:1906.06685
Abstract
Background Based Conversations (BBCs) have been developed to make dialogue systems generate more informative and natural responses by leveraging background knowledge. Existing methods for BBCs can be grouped into two categories: extraction-based methods and generation-based methods. The former extract spans frombackground material as responses that are not necessarily natural. The latter generate responses thatare natural but not necessarily effective in leveraging background knowledge. In this paper, we focus on generation-based methods and propose a model, namely Context-aware Knowledge Pre-selection (CaKe), which introduces a pre-selection process that uses dynamic bi-directional attention to improve knowledge selection by using the utterance history context as prior information to select the most relevant background material. Experimental results show that our model is superior to current state-of-the-art baselines, indicating that it benefits from the pre-selection process, thus improving in-formativeness and fluency.
SCAI 2019 workshop paper
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Bidirectional Attention Flow for Machine Comprehension
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
- Learning Recurrent Span Representations for Extractive Question Answering
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
Cited by in corpus (5)
- A Survey of Document Grounded Dialogue Systems (DGDS)
- RefNet: A Reference-aware Network for Background Based Conversation
- Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
- Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
- A Compare Aggregate Transformer for Understanding Document-grounded Dialogue