Response Generation via Structure-Aware Constraints

Abstract

End-to-end neural modeling with the encoder-decoder architecture has shown great promise in response generation. However, it often generates dull and generic responses due to its failure to effectively perceive various kinds of act, sentiment, and topic information. To address these challenges, we propose a response-generation model with structure-aware constraints to capture the structure of dialog and generate a better response with various constraints of the act, sentiment, and topic. In particular, given an utterance sequence, we first learn the representation of each utterance in the encoding stage. We then learn the turn, speaker, and dialog representation from the utterance representations and construct the structure of dialog. Third, we employ an attention mechanism to extract the constraints of act, sentiment, and topic based on the structure of the dialog. Finally, we utilize these structure-aware constraints to control the response-generation process in decoding stage. Extensive experimental results validate the superiority of our proposed model against the state-of-the-art baselines. In addition, the results also show that the proposed model can generate responses with more appropriate content based on the structure-aware constraints.