arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12771cs.CL
收藏

学习扩展:信息寻求对话中强化的伪相关反馈选择

Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations

Alibaba Group(阿里巴巴集团);East China Normal University(华东师范大学);University of Massachusetts at Amherst(马萨诸塞大学阿默斯特分校)

Haojie Pan, Cen Chen, Chengyu Wang, Minghui Qiu, Liu Yang, Feng Ji, Jun Huang

摘要:

信息搜索会话系统在现实世界的应用中越来越受欢迎,特别是对于电子商务公司。为了给用户检索到合适的响应,需要计算候选响应与用户查询与历史对话语句的匹配度。由于上下文通常比响应长得多,因此有必要用更丰富的信息扩展响应(通常很短)。近年来伪相关反馈(PRF)的研究表明,它在搜索引擎的查询扩展中是有效的,因此我们考虑使用PRF信息来扩展响应。然而,现有的PRF方法要么是基于启发式规则或需要大量的人工标记,这是不适合解决我们的任务。为了缓解这个问题,我们将响应扩展的PRF选择视为一个学习任务,并提出了一种强化学习方法,可以在没有任何人为注释的情况下以端到端的方式进行训练。更具体地说,我们提出了一个加强选择器提取有用的PRF条款,以提高响应候选人和一个基于BERT的响应排名的PRF增强响应。排序器的性能作为奖励,引导选择器提取有用的PRF术语,从而提高整体任务性能。在标准基准测试和商业数据集上的大量实验证明了我们的增强型PRF项选择器与其他潜在的软或硬选择方法相比的优越性。案例研究和定量分析表明,我们的模型是能够选择有意义的PRF条款,以扩大响应候选人,也取得了最好的结果相比,所有基线的各种评估指标。我们还将我们的方法部署在一家电子商务公司的在线生产上,这比现有的在线排名系统有了显着的改进。

英文摘要:

Information-seeking conversation systems are increasingly popular in real-world applications, especially for e-commerce companies. To retrieve appropriate responses for users, it is necessary to compute the matching degrees between candidate responses and users' queries with historical dialogue utterances. As the contexts are usually much longer than responses, it is thus necessary to expand the responses (usually short) with richer information. Recent studies on pseudo-relevance feedback (PRF) have demonstrated its effectiveness in query expansion for search engines, hence we consider expanding response using PRF information. However, existing PRF approaches are either based on heuristic rules or require heavy manual labeling, which are not suitable for solving our task. To alleviate this problem, we treat the PRF selection for response expansion as a learning task and propose a reinforced learning method that can be trained in an end-to-end manner without any human annotations. More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses. The performance of the ranker serves as a reward to guide the selector to extract useful PRF terms, which boosts the overall task performance. Extensive experiments on both standard benchmarks and commercial datasets prove the superiority of our reinforced PRF term selector compared with other potential soft or hard selection methods. Both case studies and quantitative analysis show that our model is capable of selecting meaningful PRF terms to expand response candidates and also achieving the best results compared with all baselines on a variety of evaluation metrics. We have also deployed our method on online production in an e-commerce company, which shows a significant improvement over the existing online ranking system.

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。

↑