DoTAT: A Domain-oriented Text Annotation ToolDownload PDF

Anonymous

16 Oct 2021 (modified: 05 May 2023)ACL ARR 2021 October Blind SubmissionReaders: Everyone
Abstract: We propose DoTAT, a domain-oriented text annotation tool. The tool designs and implements functions heavily in need in domain-oriented information extraction. Firstly, the tool supports a multi-person collaborative process with automatically merging and review, which can greatly improve the annotation accuracy. Secondly, the tool provides annotation of event, nested event, and nested entity, which are frequently required in domain-related text structuring tasks. Finally, DoTAT provides visualized annotation specification definition, automatic batch annotation, and iterative annotation to improve annotation efficiency. Experiments on the ACE2005 dataset show that DoTAT can reduce the event annotation time by 19.7% compared with existing annotation tools. The accuracy without review is 84.09%, 1.35% higher than Brat, and 2.59% higher than Webanno. The accuracy of DoTAT even reaches 93.76% with the review. The demonstration video can be accessed from https://ecust-nlp-docker.oss-cn-shanghai.aliyuncs.com/dotat_demo.mp4. A live demo website is available at https://github.com/FXLP/MarkTool.
0 Replies

Loading