Code for "A Simple but Effective System for Multi-format Information Extraction"(NLPCC 2021) and LIC-2021（2021语言与智能技术竞赛：多形态信息抽取任务）.
Our approach is evaluated with 'DuIE2.0', 'DuEE1.0' and 'DuEE-fin' and ranks No.4. The dataset can be found in 'LUGE'.
We ensemble three public project TPLinker[1] (project is here), SPN[2] (project is here), CasRel[3] (project is here). So we don't provide our code.
Thanks for their public project.
The detail is found in EE.
The detail is found in EE-fin.
[1] Wang, Y., Yu, B., Zhang, Y., Liu, T., Zhu, H., Sun, L.: TPLinker: Single-stage joint extraction of entities and relations through token pair linking. In: Proceedings of the 28th International Conference on Computational Linguistics. pp. 1572–1582. International Committee on Computational Linguistics, Barcelona, Spain (Online) (Dec 2020)
[2] Sui, D., Chen, Y., Liu, K., Zhao, J., Zeng, X., Liu, S.: Joint Entity and Relation Extraction with Set Prediction Networks. arXiv e-prints arXiv:2011.01675 (Nov 2020)
[3] Wei, Z., Su, J., Wang, Y., Tian, Y., Chang, Y.: A novel cascade binary tagging framework for relational triple extraction. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 1476–1488. Association for Computational Linguistics, Online (Jul 2020)