Construction of a Chinese Corpus for Multi-Type Economic Event Relation
Construction of a Chinese Corpus for Multi-Type Economic Event Relation
复制标题
DOI：
10.1145/3527240
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Qi-Zhi Wan;Changxuan Wan;Keli Xiao;Dexi Liu;Qing Liu;Jiangling Deng;Wenkang Luo;Rong Hu
中科院分区：
文献类型：
--
作者：
Qi-Zhi Wan;Changxuan Wan;Keli Xiao;Dexi Liu;Qing Liu;Jiangling Deng;Wenkang Luo;Rong Hu
本文构建了中国经济事件树库（CEETB），重点揭示经济和金融事件及其相互关系。研究经济事件之间的关系不仅有利于经济学的学术研究和实践，也有利于许多其他科学领域。与经济有关的文本的特点（例如，丰富的较长企业名称和术语）和中文专业（例如，长句中的成分省略）已经在事件关系提取任务中导致了挑战。现有的包含经济事件关系的中文语料库主要集中在金融领域（例如，股票市场），只涵盖了几种事件类型。为了支持可能涉及中文经济文本分析的研究，我们的CEETB遵循精心设计的过程构建。首先，基于实践和研究的需要，我们总结了经济语篇中九种不同类型的事件关系和四种成分省略。在此基础上，提出了一个优秀的标注方案，对标注的模型、策略和过程进行了透明化，并对CEETB语料进行了统计分析和质量评价。最后，为了证明所构建的语料库在实际应用中的优势，我们对五个SOTA事件关系抽取模型进行了实验。
We construct a Chinese Economic Event Treebank (CEETB), focusing on revealing economic and finance events and their relations. Investigating economic event relations will benefit academic research and practice in not just economics but many other scientific areas. The characteristics of economic-related texts (e.g., abundant longer enterprises names and terms) and the Chinese language speciality (e.g., component ellipsis in long sentences) have resulted in challenges in the event relation extraction task. Existing Chinese corpora containing economic event relations mainly focused on finance areas (e.g., the equity market) and only covered a few event types. To support research that may involve economic text analysis in Chinese, our CEETB is constructed following a carefully designed process. First, based on practical and research requirements, we summarize nine different types of event relations and four types of component ellipses in economic texts. Then, an excellent annotation scheme is presented to hyalinize the model, strategy, and process in annotation, followed by statistical analysis and quality evaluation for the CEETB corpus. Finally, to demonstrate the strengths of the constructed corpus in practical applications, we conduct experiments on five SOTA models for event relation extraction.