Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
This addresses information extraction for NLP applications, but it appears incremental as it builds on existing joint extraction methods.
The authors tackled joint extraction of entities and relations by proposing a novel tagging scheme that converts the task into a tagging problem, and their end-to-end model achieved the best results on a public dataset.
Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. Then, based on our tagging scheme, we study different end-to-end models to extract entities and their relations directly, without identifying entities and relations separately. We conduct experiments on a public dataset produced by distant supervision method and the experimental results show that the tagging based methods are better than most of the existing pipelined and joint learning methods. What's more, the end-to-end model proposed in this paper, achieves the best results on the public dataset.