基于检索结果融合机制的对话生成模型

Response Generation by Retrieved Response Fusion Mechanism

对话生成模型是对话系统中十分重要的组件。传统的对话生成模型仅利用用户的输入信息生成回复,这导致在生成过程中常会出现无意义的万能回复。最近有工作尝试将检索的方法融入生成模型从而提高模型的生成质量,但这些方法往往将重点放在如何编辑检索结果上,没有考虑检索结果与用户查询之间的语义空间差别。为解决这一问题,该文提出了基于检索结果融合的对话生成模型。模型首先利用双向长短时记忆网络对检索结果进行编码,并提出了具有融合机制的长短时记忆网络(fusion-LSTM)。该机制将检索结果在模型内部与对话文本相结合,以更好地将检索到的信息融入到生成模型中。实验结果表明,该方法在自动评价指标和人工评价指标中都明显优于基线方法。

Response generation is an important component of the dialogue system. To better combine the retrieval-based model with a generation-based model, this paper proposes a response generative model via the retrieved response fusion mechanism. The model uses bidirectional LSTM to encode the retrieved response, and then this paper proposes a Long Short-Term Memory network with a fusion mechanism(fusion-LSTM). This mechanism fuses retrieval results with dialogue text within the model to better integrate the retrieved information into the generative model. The experimental results show that this method is superior to the baseline methods in both automatic and human evaluation.