Generating Informative Dialogue Responses with Keywords-Guided Networks

Recently, open-domain dialogue systems have attracted growing attention. Most of them use the sequence-to-sequence (Seq2Seq) architecture to generate dialogue responses. However, traditional Seq2Seq-based open-domain dialogue models tend to generate generic and safe responses, which are less informative, unlike human responses. In this paper, we propose a simple but effective Keywords-guided Sequence-to-sequence model (KW-Seq2Seq) which uses keywords information as guidance to generate open-domain dialogue responses. Specifically, given the dialogue context, KW-Seq2Seq first uses a keywords decoder to predict a sequence of topic keywords, and then generates the final response under the guidance of them. Extensive experiments demonstrate that the keywords information can facilitate the model to produce more informative, coherent, and fluent responses, yielding substantive gain in both automatic and human evaluation metrics.