对话中融入丰富历史信息的回应选择

Towards Better Response Selection in Dialogue via Rich Historical Information

对话是一个交互的过程,回应选择旨在根据已有对话上文选择合适的回应,是自然语言处理领域的研究热点。已有研究取得了一定的成功,但仍存在两个突出的问题:一是历史信息与备选回应间的关联关系未得到充分利用;二是对话历史的潜在语义信息挖掘不够。针对问题一,该文同时考虑对话的历史信息与备选回应信息,借助交叉注意力机制实现两者的软对齐,从而对它们之间的关联关系进行有效捕捉;针对问题二,一方面借助多头自注意力机制从多个不同视角捕获对话历史的潜在语义信息,另一方面借助高速路神经网络实现多种信息的有效桥接,在深度挖掘语义信息的同时保证信息的完整。在Ubuntu Corpus V1数据集上的对比实验表明了该方法的有效性,模型取得了88.66%的R_(10)@1值,90.06%的R_(10)@2值和95.15%的R_(10)@5值。

Response selection for dialogue is a popular research issue in the field of NLP, which is aimed at selecting appropriate responses based on the existing dialogue. Existing researches are defected in two aspects: 1) insufficient utilization of the correlation between historical information and alternative responses and, 2) insufficient mining of potential semantic information in dialogue history. To deal with the first issue, this paper considers both the historical information and the alternative response information in the dialogue, by the cross-attention mechanism to effectively capture the relationship between them. For the second issue, this paper employs the multi-head self-attention mechanism to capture the latent semantic information of the conversation history from multiple different perspectives, and the highway network to effectively bridge a variety of information to ensure the integrity of the information. Experiments show the proposed method achieves a 88.66%R_(10)@1-score,a 90.06%R_(10)@2-score and a 95.15%R_(10)@5-score on the Ubuntu Corpus V1 dataset.