An Information Retrieval Approach to Short Text Conversation
Zongcheng Ji Zhengdong Lu Hang Li Noah’s Ark Lab, Huawei Technologies, Beijing, China Noah’s Ark Lab, Huawei Technologies, Hong Kong, China
Abstract
Human computer conversation is regarded as one of the most difficult problems in artificial intelligence. In this paper, we address one of its key sub-problems, referred to as short text conversation, in which given a message from human, the computer returns a reasonable response to the message. We leverage the vast amount of short conversation data available on social media to study the issue. We propose formalizing short text conversation as a search problem at the first step, and employing state-of-the-art information retrieval (IR) techniques to carry out the task. We investigate the significance as well as the limitation of the IR approach. Our experiments demonstrate that the retrieval-based model can make the system behave rather “intelligently”, when combined with a huge repository of conversation data from social media.
中文速览
让计算机像人一样回复短消息是人工智能的核心难题之一，核心障碍在于缺乏大规模真实对话数据。研究团队将这一问题定义为"短文本对话"（Short Text Conversation, STC），并把它转化为一个信息检索（Information Retrieval, IR）任务——不凭空生成回复，而是从微博海量帖子-评论对中检索出最合适的回复。他们设计了一套三阶段框架：先用基础匹配模型快速缩小候选集，再用翻译模型、隐语义空间模型、深度匹配模型和专为STC设计的主题词模型对候选回复打分，最后用排序学习（Learning to Rank）综合各分数选出最佳回复。在微博真实数据集上的大规模实验表明，该检索式方法在第一位准确率（Precision@1）上达到0.64，证明结合海量社交媒体数据和先进IR技术后，系统已能产生相当"像人"的对话效果，同时也揭示了纯检索方式在语义理解上的局限，为后续生成式对话研究提供了重要基线和公开数据集。
原文 arXiv:1408.6988;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1408.6988v1