当前位置: X-MOL 学术IEEE Trans. Neural Netw. Learn. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Keep and Select: Improving Hierarchical Context Modeling for Multi-Turn Response Generation
IEEE Transactions on Neural Networks and Learning Systems ( IF 10.4 ) Pub Date : 2021-09-29 , DOI: 10.1109/tnnls.2021.3112700
Yanxiang Ling , Fei Cai , Jun Liu , Honghui Chen , Maarten de Rijke

Hierarchical context modeling plays an important role in the response generation for multi-turn conversational systems. Previous methods mainly model context as multiple independent utterances and rely on attention mechanisms to obtain the context representation. They tend to ignore the explicit responds-to relationships between adjacent utterances and the special role that the user’s latest utterance (the query) plays in determining the success of a conversation. To deal with this, we propose a multi-turn response generation model named KS-CQ, which contains two crucial components, the Keep and the Select modules, to produce a neighbor-aware context representation and a context-enriched query representation. The Keep module recodes each utterance of context by attentively introducing semantics from its prior and posterior neighboring utterances. The Select module treats the context as background information and selectively uses it to enrich the query representing process. Extensive experiments on two benchmark multi-turn conversation datasets demonstrate the effectiveness of our proposal compared with the state-of-the-art baselines in terms of both automatic and human evaluations.

中文翻译:

保留和选择:改进多轮响应生成的分层上下文建模

分层上下文建模在多轮对话系统的响应生成中发挥着重要作用。以前的方法主要将上下文建模为多个独立的话语,并依靠注意力机制来获取上下文表示。他们倾向于忽略相邻话语之间的明确响应关系以及用户最新话语(查询)在确定对话成功方面所扮演的特殊角色。为了解决这个问题,我们提出了一种名为 KS-CQ 的多轮响应生成模型,它包含两个关键组件:Keep 和 Select 模块,以生成邻居感知的上下文表示和上下文丰富的查询表示。Keep 模块通过仔细引入前后相邻话语的语义来重新编码上下文的每个话语。Select 模块将上下文视为背景信息,并有选择地使用它来丰富查询表示过程。对两个基准多轮对话数据集的广泛实验证明了我们的建议在自动和人工评估方面与最先进的基线相比的有效性。
更新日期:2021-09-29
down
wechat
bug