TripleNet:三重注意力网络在基于检索的聊天机器人中的多轮响应选择
TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots
摘要:
我们认为在选择响应的上下文中不同的话语的重要性通常取决于当前查询。在本文中,我们提出了一个模型TripleNet来完全建模的任务与三元组<上下文,查询,响应>,而不是<上下文,响应>在以前的作品。TripleNet的核心是一种新的注意力机制,称为三重注意力,用于在四个级别上对三重注意力之间的关系进行建模。新机制基于对其他两个元素的关注同时对称地更新每个元素的表示。我们将以响应为中心的三元组<C,Q,R>从字符匹配到上下文级别进行预测。在两个大规模多轮响应选择数据集上的实验结果表明,该模型的性能明显优于现有方法。TripleNet源代码可在https://github.com/wtma/TripleNet上获得
英文摘要:
We consider the importance of different utterances in the context for selecting the response usually depends on the current query. In this paper, we propose the model TripleNet to fully model the task with the triple <context, query, response> instead of <context, response> in previous works. The heart of TripleNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels. The new mechanism updates the representation for each element based on the attention with the other two concurrently and symmetrically. We match the triple <C, Q, R> centered on the response from char to context level for prediction. Experimental results on two large-scale multi-turn response selection datasets show that the proposed model can significantly outperform the state-of-the-art methods. TripleNet source code is available at https://github.com/wtma/TripleNet
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。