Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System
Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System
复制标题
DOI：
10.1145/3077136.3080843
复制
发表时间：
2017-08
期刊：
影响因子：
--
通讯作者：
Rui Yan;Dongyan Zhao;E. Weinan
中科院分区：
文献类型：
--
作者：
Rui Yan;Dongyan Zhao;E. Weinan
对话系统变得越来越重要，因为它们使用自然语言在人类和计算机之间提供了简单的交互界面。建立一个具有足够智能的对话系统具有挑战性，需要丰富的资源，包括获取大数据和跨学科技术，例如信息检索和自然语言处理。随着Web 2.0的繁荣，海量数据极大地促进了数据驱动的方法，例如人机对话系统的深度学习。由于网络资源的多样性，基于检索的对话系统将从巨大的存储库中为任何用户输入提供至少一些结果。给定人类发出的消息（即查询），传统的对话系统将在经过充分的训练和学习如何响应后提供响应。在本文中，我们提出了对话系统的一项新任务：以下一个话语建议为特征的响应排名的联合学习。我们假设新的对话模式更加主动并保持用户参与。我们在实验中检验这个假设。此外，为了解决联合学习任务，我们提出了一种新颖的双 LSTM 链模型来同时耦合响应排名和下一个话语建议。从实验结果中，我们证明了所提出的任务的有用性和所提出的模型的有效性。
Conversation systems are of growing importance since they enable an easy interaction interface between humans and computers: using natural languages. To build a conversation system with adequate intelligence is challenging, and requires abundant resources including an acquisition of big data and interdisciplinary techniques, such as information retrieval and natural language processing. Along with the prosperity of Web 2.0, the massive data available greatly facilitate data-driven methods such as deep learning for human-computer conversation systems. Owing to the diversity of Web resources, a retrieval-based conversation system will come up with at least some results from the immense repository for any user inputs. Given a human issued message, i.e., query, a traditional conversation system would provide a response after adequate training and learning of how to respond. In this paper, we propose a new task for conversation systems: joint learning of response ranking featured with next utterance suggestion. We assume that the new conversation mode is more proactive and keeps user engaging. We examine the assumption in experiments. Besides, to address the joint learning task, we propose a novel Dual-LSTM Chain Model to couple response ranking and next utterance suggestion simultaneously. From the experimental results, we demonstrate the usefulness of the proposed task and the effectiveness of the proposed model.