Hierarchical Recurrent Attention Network for Response Generation
This work improves chatbot response generation by better capturing context importance, though it is incremental as it builds on existing hierarchical models.
The paper tackles the problem of generating relevant responses in multi-turn chatbots by addressing the differential importance of words and utterances in conversation context, resulting in a model that significantly outperforms state-of-the-art methods in both automatic and human evaluations.
We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact that words and utterances in the context are differentially important. As a result, they may lose important information in context and generate irrelevant responses. We propose a hierarchical recurrent attention network (HRAN) to model both aspects in a unified framework. In HRAN, a hierarchical attention mechanism attends to important parts within and among utterances with word level attention and utterance level attention respectively. With the word level attention, hidden vectors of a word level encoder are synthesized as utterance vectors and fed to an utterance level encoder to construct hidden representations of the context. The hidden vectors of the context are then processed by the utterance level attention and formed as context vectors for decoding the response. Empirical studies on both automatic evaluation and human judgment show that HRAN can significantly outperform state-of-the-art models for multi-turn response generation.