arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.02364cs.CLcs.AIcs.NE
收藏

短文本会话的神经应答机

Neural Responding Machine for Short-Text Conversation

Noah’s Ark Lab(诺亚方舟实验室);Huawei Technologies Co. Ltd.(华为技术有限公司)

Lifeng Shang, Zhengdong Lu, Hang Li

摘要:

我们提出了神经应答机(NRM),一个基于神经网络的短文本会话响应生成器。NRM采用了通用的编码器-解码器框架:它将响应的生成形式化为基于输入文本的潜在表示的解码过程,而编码和解码都是用递归神经网络(RNN)实现的。NRM使用从微博服务收集的大量单轮对话数据进行训练。实证研究表明,NRM可以生成语法正确和内容上的适当的反应超过75%的输入文本,在相同的设置,包括基于检索和基于SMT的模型的最先进的性能优于。

英文摘要:

We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it formalizes the generation of response as a decoding process based on the latent representation of the input text, while both encoding and decoding are realized with recurrent neural networks (RNN). The NRM is trained with a large amount of one-round conversation data collected from a microblogging service. Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming state-of-the-arts in the same setting, including retrieval-based and SMT-based models.

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。

↑