arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12484cs.CL
收藏

会话式机器阅读的显式记忆跟踪器及其粗到细推理

Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

The Chinese University of Hong Kong(香港中文大学);Salesforce Research(Salesforce 研究院)

Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael R. Lyu, Steven C. H. Hoi

摘要:

对话式机器阅读的目标是回答给定知识库文本的用户问题,这可能需要提出澄清问题。现有的方法是有限的,在他们的决策,由于斗争中提取问题相关的规则和推理。在本文中,我们提出了一个新的对话式机器阅读框架,其中包括一个新的显式记忆跟踪器(EMT),以跟踪规则文本中列出的条件是否已经满足作出决定。此外,我们的框架产生澄清问题,采用了由粗到细的推理策略,利用语义级蕴涵分数加权令牌级分布。在ShARC基准(盲,保持)测试集上,EMT实现了74.6%的微平均决策准确率和49.5 BLEU4的最新结果。我们还表明,EMT是更可解释的可视化的蕴涵为导向的推理过程中的会话流。代码和模型在https://github.com/Yifan-Gao/explicit_memory_tracker上发布。

英文摘要:

The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited in their decision making due to struggles in extracting question-related rules and reasoning about them. In this paper, we present a new framework of conversational machine reading that comprises a novel Explicit Memory Tracker (EMT) to track whether conditions listed in the rule text have already been satisfied to make a decision. Moreover, our framework generates clarification questions by adopting a coarse-to-fine reasoning strategy, utilizing sentence-level entailment scores to weight token-level distributions. On the ShARC benchmark (blind, held-out) testset, EMT achieves new state-of-the-art results of 74.6% micro-averaged decision accuracy and 49.5 BLEU4. We also show that EMT is more interpretable by visualizing the entailment-oriented reasoning process as the conversation flows. Code and models are released at https://github.com/Yifan-Gao/explicit_memory_tracker.

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。

↑