arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.00897cs.CL
收藏

领域感知神经对话系统

Domain Aware Neural Dialog System

University of Pennsylvania(宾夕法尼亚大学)

Sajal Choudhary, Prerna Srivastava, Lyle Ungar, João Sedoc

摘要:

我们调查的任务是建立一个域感知聊天系统,该系统在不同的域组成的对话中生成智能响应。在这种情况下,域是对话的主题或主题。为了实现这一点,我们提出了DOM-Seq 2Seq,一种基于使用域靶向序列到序列模型的新技术的域感知神经网络模型(Sutskever et al.,2014)和域分类器。该模型从当前话语和先前话语的域中捕获特征,以促进相关响应的形成。我们评估我们的模型的自动指标,并比较我们的性能与Seq 2Seq模型。

英文摘要:

We investigate the task of building a domain aware chat system which generates intelligent responses in a conversation comprising of different domains. The domain, in this case, is the topic or theme of the conversation. To achieve this, we present DOM-Seq2Seq, a domain aware neural network model based on the novel technique of using domain-targeted sequence-to-sequence models (Sutskever et al., 2014) and a domain classifier. The model captures features from current utterance and domains of the previous utterances to facilitate the formation of relevant responses. We evaluate our model on automatic metrics and compare our performance with the Seq2Seq model.

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。

↑