An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation

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 read more

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Generation DailyDialog AEM+Attention BLEU-1 14.17 # 1
BLEU-2 5.69 # 1
BLEU-3 3.78 # 1
BLEU-4 2.84 # 1

Methods


No methods listed for this paper. Add relevant methods here