摘要
现有工作利用神经网络构建了各种检索模型,取得了一定的成功,但仍存在注入模型信息筛选不充分、引入噪声和对已知内容的潜在语义信息、时序关系挖掘不充分问题。针对上述问题,提出了基于深度多匹配网络的多轮对话回复模型(DMMN)。该模型将上下文与知识作为对候选回复的查询,在三者编码之后提出预匹配层,采用单向交叉注意力机制分别筛选出基于知识感知的上下文与基于上下文感知的知识,识别两者中重要的信息。将候选回复与以上两者交互作用之后,进行特征聚合阶段,一方面借助额外BiLSTM网络捕获基于回复的上下文对话信息间的时序信息,另一方面借助带门控的注意力机制挖掘基于回复的知识间的语义信息,增强匹配特征信息。最后,融合上述表示特征。在原始的和修改后的Persona-Chat数据集上性能评测结果显示,与现有方法相比,该模型召回率得到了进一步的提高,检索出的回复效果更好。
There are still issues with insufficient model information screening that introduces noise,insufficient mining of potential semantic information,and insufficient consideration of the temporal relationships of known contents,although existing works have constructed a variety of retrieval models using neural networks with some success.The research suggested a multi-turn dialogue response model based on a deep multi-matching network(DMMN)to overcome the aforementioned problems.The model took context and knowledge as queries to candidate responses,proposed a pre-matching layer after encoding all three,and used a one-way cross-attention mechanism to filter knowledge-aware context and context-aware knowledge,respectively,to identify the important information in both.After the candidate response had interacted with the aforementioned two,it conducted a feature aggregation phase to improve the matching feature information by mining the semantic information between the response-based knowledge and the attention mechanism with gating on the one hand and the temporal information between the response-based contextual dialogue messages with the aid of an additional BiLSTM network on the others.Finally,the representation features mentioned above were combined.According to the performance evaluation results on the original and revised Persona-Chat datasets,the model has further increased the recall rate and recovered better responses when compared to existing approaches.
作者
刘超
李婉
Liu Chao;Li Wan(School of Computer Science&Engineering,Chongqing University of Technology,Chongqing 400054,China)
出处
《计算机应用研究》
CSCD
北大核心
2023年第8期2393-2398,共6页
Application Research of Computers
基金
国家教育考试科研规划课题(GJK2019006)。
