@article{Xu2022, 
author = {Yang Xu and Boming Xia and Yueliang Wan and Fan Zhang and Jiabo Xu and Huansheng Ning},
title = {CDCAT: A Multi-Language Cross-Document Entity and Event Coreference Annotation Tool},
year = {2022},
journal = {Tsinghua Science and Technology},
volume = {27},
number = {3},
pages = {589-598},
keywords = {natural language processing, event coreference, entity coreference, manual annotation tool},
url = {https://www.sciopen.com/article/10.26599/TST.2020.9010060},
doi = {10.26599/TST.2020.9010060},
abstract = {A tool for the manual annotation of cross-document entity and event coreferences that helps annotators to label mention coreference relations in text is essential for the annotation of coreference corpora. To the best of our knowledge, CROss-document Main Events and entities Recognition (CROMER) is the only open-source manual annotation tool available for cross-document entity and event coreferences. However, CROMER lacks multi-language support and extensibility. Moreover, to label cross-document mention coreference relations, CROMER requires the support of another intra-document coreference annotation tool known as Content Annotation Tool, which is now unavailable. To address these problems, we introduce Cross-Document Coreference Annotation Tool (CDCAT), a new multi-language open-source manual annotation tool for cross-document entity and event coreference, which can handle different input/output formats, preprocessing functions, languages, and annotation systems. Using this new tool, annotators can label a reference relation with only two mouse clicks. Best practice analyses reveal that annotators can reach an annotation speed of 0.025 coreference relations per second on a corpus with a coreference density of 0.076 coreference relations per word. As the first multi-language open-source cross-document entity and event coreference annotation tool, CDCAT can theoretically achieve higher annotation efficiency than CROMER.}
}