arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.06841cs.CLcs.AIcs.LG
收藏

开放信息抽取中部分观测数据的句法鲁棒训练

Syntactically Robust Training on Partially-Observed Data for Open Information Extraction

Tsinghua University(清华大学);University of California, San Diego(加利福尼亚大学圣迭戈分校)

Ji Qi, Yuxiang Chen, Lei Hou, Juanzi Li, Bin Xu

摘要:

开放式信息抽取模型在充分的监督下显示出有希望的结果。然而,这些模型面临着一个根本性的挑战,即与现实世界相比,训练数据的语法分布是部分可观察的。在本文中,我们提出了一个语法上强大的训练框架,使模型能够在基于不同释义生成的语法丰富的分布上进行训练。针对释义过程中知识变形的问题,提出了基于语义相似度匹配和句法树遍历的知识还原算法。该训练框架可普遍应用于其他句法部分可观测域。基于所提出的框架,我们构建了一个新的评估集,称为CaRB-AutoPara,这是一个与真实世界设置一致的语法多样的数据集,用于验证模型的鲁棒性。实验结果表明,该模型的性能随着句法分布差异的增加而下降,而我们的框架给出了一个鲁棒的边界。源代码可在https://github.com/qijimrc/RobustOIE上公开获得。

英文摘要:

Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary. The source code is publicly available at https://github.com/qijimrc/RobustOIE.

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。

↑