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.
Improving Zero-Shot Event Extraction via Sentence Simplification
ACLED和Our World in Data等网站的成功证明了从新闻、社交媒体、博客和论坛等形式的大量文本数据中以结构化格式提取事件的巨大效用。事件提取可以为正在发生的地缘政治危机提供一个窗口,并产生可操作的情报。随着大型预训练语言模型的激增,机器阅读理解(MRC)近年来已成为事件提取的新范式。在这种方法中,事件论元提取被框定为一个提取的问题回答任务。基于MRC的方法的关键优点之一是其执行zero-shot提取的能力。然而,长期依赖性的问题,即,触发词和论元词之间较大的词汇距离以及处理句法复杂的句子的困难困扰着基于MRC的方法。在本文中,我们提出了一种通用的方法来提高性能的MRC为基础的事件提取进行无监督的句子简化指导的MRC模型本身。我们在ICEWS地缘政治事件提取数据集上评估了我们的方法,特别注意“演员”和“目标”参数角色。我们展示了如何这样的上下文简化可以提高基于MRC的事件提取的性能超过5%的演员提取和超过10%的目标提取。
Bootstrapping Relation Extractors using Syntactic Search by Examples
Allen Institute for AI(艾伦人工智能研究所);Bar Ilan University(巴伊兰大学)
自然语言处理中神经网络的出现带来了监督式关系抽取的实质性改进。然而,获得足够数量的训练数据仍然是一个关键挑战。在这项工作中,我们提出了一个引导训练数据集的过程,可以由非NLP专家快速执行。我们利用搜索引擎的语法图(如Shlain et al.(2020)),它揭示了一个友好的例子语法。我们使用这些来获得积极的例子,通过搜索的句子,在句法上类似于用户输入的例子。我们将这种技术应用于TACRED和DocRED的关系,并表明所得到的模型与手动注释数据和从远程监督获得的数据上训练的模型具有竞争力。该模型还优于使用NLG数据增强技术训练的模型。使用NLG方法扩展基于搜索的方法进一步改善了结果。
Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Beijing University of Posts and Telecommunications(北京邮电大学)
Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction
Institute for Advanced Studies(先进研究院);Universiti Malaya(马来大学);School of Information Engineering(信息工程学院);Suqian University(宿州学院);Digitization Department(数字化部门)