An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
arXiv:1808.08795
Abstract
Generating semantically coherent responses is still a major challenge in dialogue generation. Different from conventional text generation tasks, the mapping between inputs and responses in conversations is more complicated, which highly demands the understanding of utterance-level semantic dependency, a relation between the whole meanings of inputs and outputs. To address this problem, we propose an Auto-Encoder Matching (AEM) model to learn such dependency. The model contains two auto-encoders and one mapping module. The auto-encoders learn the semantic representations of inputs and responses, and the mapping module learns to connect the utterance-level representations. Experimental results from automatic and human evaluations demonstrate that our model is capable of generating responses of high coherence and fluency compared to baseline models. The code is available at https://github.com/lancopku/AMM
arXiv commentAccepted by EMNLP 2018
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- A Neural Conversational Model
- Effective Approaches to Attention-based Neural Machine Translation
- DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
- Deep Reinforcement Learning for Dialogue Generation
- Adversarial Learning for Neural Dialogue Generation
- Text Matching as Image Recognition
- Global Encoding for Abstractive Summarization
Cited by in corpus (4)
- DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
- A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
- Generating Dialogue Responses from a Semantic Latent Space
- Identifying High-Quality Chinese News Comments Based on Multi-Target Text Matching Model