The pipelined approach to biomedical event extraction has the problem of error propagation, and the associations among these subtasks is ignored. In order to solve these problems, this paper adopts an end-to-end approach to model three independent sub-tasks, namely trigger recognition, argument detection and event evaluation, simultaneously, and conducts training in a joint way. We introduce the dependency information of the sentence to capture the relevance of multiple events in the same sentence. Therefore, the proposed method converts the dependency parse tree into a graph and uses the graph neural network based on multiple heads mechanism to model the graph information. Experimental results show that this method is effective in event extraction tasks on the three major biological data sets.
KIMJ D, OHTAT, PYYSALOS, et al. Overview of BioNLP’09 shared task on event extraction[C]//Proceedings of the Workshop on BioNLP Shared Task - BioNLP’09. Stroudsburg: Association for Computational Linguistics, 2009: 1-9. DOI:10.3115/1572340.1572342 .
[2]
KIMJ D, PYYSALOS, OHTAT, et al. Overview of bionlp shared task 2011[C]//Proceedings of the BioNLP Shared Task 2011 Workshop. Stroudsburg :Association for Computational Linguistics,2011: 1-6. DOI: 10.1111/j.1467-8640.2011.00398.x .
[3]
NÉDELLECC, BOSSYR, KIMJ D, et al. Overview of bionlp shared task 2013[C]//Proceedings of the BioNLP Shared Task 2013 Workshop. Stroudsburg :Association for Computational Linguistics,2013: 1-7.
[4]
CHAIXE, DUBREUCQB, FATIHIA, et al. Overview of the regulatory network of plant seed development (SeeDev) task at the BioNLP shared task 2016[C]//Proceedings of the 4th BioNLP Shared Task Workshop. Stroudsburg: Association for Computational Linguistics, 2016: 1-11. DOI:10.18653/v1/w16-3001 .
[5]
KILICOGLUH, BERGLERS. Syntactic dependency based heuristics for biological event extraction [C]//Proceedings of the Workshop on BioNLP Shared Task-BioNLP’09. Stroudsburg: Association for Computational Linguistics, 2009: 119-127. DOI:10.3115/1572340.1572361 .
[6]
XUANQ P, MINHQ L, BAOQ. A Hybrid approach for biomedical event extraction[C]//Proceedings of the BioNLP Shared Task 2013 Workshop. Stroudsburg:Association for Computational Linguistics,2013:121-124.
[7]
QUOCB, DAVIDC, ERIKM, et al. A fast rule-based approach for biomedical event extraction[C]// Proceedings of the BioNLP Shared Task 2013 Workshop. Stroudsburg :Association for Computational Linguistics, 2013: 104-108.
[8]
BJÖRNEJ, HEIMONENJ, GINTERF, et al. Extracting complex biological events with rich graph-based feature sets[C]//Proceedings of the Workshop on BioNLP Shared Task - BioNLP’09. Stroudsburg: Association for Computational Linguistics, 2009: 10-18. DOI:10.3115/1572340.1572343 .
[9]
KAIH, SOFIEV L, TAPIOS, et al. EVEX in ST’13: Application of a large-scale text mining resource to event extraction and network construction[C]// Proceedings of the BioNLP Shared Task 2013 Workshop. Stroudsburg:Association for Computational Linguistics,2013:26-34.
[10]
ZHOUD Y, ZHONGD Y. A semi-supervised learning framework for biomedical event extraction based on hidden topics[J]. Artificial Intelligence in Medicine, 2015, 64(1): 51-58. DOI:10.1016/j.artmed.2015.03.004 .
[11]
LIL S, LIUS S, QINM Y, et al. Extracting biomedical event with dual decomposition integrating word embeddings [J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2016, 13(4): 669-677. DOI:10.1109/TCBB.2015.2476876 .
[12]
LIL S, LIUY. Exploiting argument information to improve biomedical event trigger identification via recurrent neural networks and supervised attention mechanisms[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). New York: IEEE Press, 2017: 565-568. DOI:10.1109/BIBM.2017.8217711 .
[13]
LIL S, HUANGM Z, LIUY, et al. Contextual label sensitive gated network for biomedical event trigger extraction[J]. Journal of Biomedical Informatics, 2019, 95: 103221. DOI:10.1016/j.jbi.2019.103221 .
[14]
FEIH, RENY F, JID H. A tree-based neural network model for biomedical event trigger detection[J]. Information Sciences, 2020, 512(3): 175-185. DOI:10.1016/j.ins.2019.09.075 .
WEIY, LIUM F, HUH J. Biomedical event extraction based on deep contextual word representation and self-attention[J]. Computer Engineering and Science, 2020, 42(9): 1670-1679. DOI:10.3969/j.issn.1007-130X.2020.09.018(Ch ).
[17]
ELAHEHS B, ANTONIOJ Y, et al. Global locality in biomedical relation and event extraction [C]// Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing. Stroudsburg :Association for Computational Linguistics,2020:195-204.DOI:10.18653/v1/2020.bionl .
[18]
RAMPONIA, GOOT RVAN DER, LOMBARDOR, et al. Biomedical event extraction as sequence labeling[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg: Association for Computational Linguistics, 2020: 5357-5367. DOI:10.18653/v1/2020.emnlp-main.431 .
[19]
MIWAM, BANSALM. End-to-end Relation Extraction Using LSTMs on Sequences and Tree Structures[DB/OL].[2021-02-02].https://arxiv.org/pdf/1601.00770.pdf. DOI:10.18653/v1/p16-1105 .
ZHANGY K, LIUM F, HUH J. Chinese medical entity classification and relationship extraction based on joint neural network model [J]. Computer Engineering and Science, 2019, 41(6): 1110-1118. DOI:10.3969/j.issn.1007-130X.2019.06.021(Ch ).
[22]
SHAL, QIANF, CHANGB B, et al. Jointly Extracting Event Triggers and Arguments by Dependency Bridge RNN and Tensor Based Argument Interaction [DB/OL].[2021-01-02].http://shalei120.github.io/docs/sha2018Joint.pdf.
[23]
ORR J W, TADEPALLIP, FERNX L. Event Detection with Neural Networks [DB/OL].[2021-02-02].https://arxiv.org/pdf/1808.08504.pdf.
[24]
KIPFT N, WELLINGM. Semi-Supervised Classification with Graph Convolutional Networks [DB/OL].[2021-02-02].
[25]
NGUYENT H, GRISHMANR. Graph Convolutional Networks with Argument Aware Pooling for Event Detection [DB/OL].[2021-08-05].https://
[26]
LIUX, LUOZ C, HUANGH Y. Jointly multiple events extraction via attention-based graph information aggregation [C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2018: 1247-1256. DOI:10.18653/v1/d18-1156 .
[27]
YANH R, JINX L, MENGX B, et al. Event detection with multi-order graph convolution and aggregated attention [C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP). Stroudsburg: Association for Computational Linguistics, 2019: 5765-5769. DOI:10.18653/v1/d19-1582 .
[28]
CUIS Y, YUB W, LIUT W, et al. Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation [DB/OL].[2021-08-05].https://arxiv.org/pdf/2002.10757v2.pdf.
[29]
YUJ T, BOHNETB, POESIOM. Named entity recognition as dependency parsing [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 6470-6476. DOI:10.18653/v1/2020.acl-main.577 .
[30]
WANGA R, WANGJ, LINH F, et al. A multiple distributed representation method based on neural network for biomedical event extraction [J]. BMC Medical Informatics and Decision Making, 2017, 17(3): 59-66. DOI:10.1186/s12911-017-0563-9 .
[31]
PYYSALOS, OHTAT, RAKR, et al. Overview of the cancer genetics and pathway curation tasks of BioNLP shared task 2013 [J]. BMC Bioinformatics, 2015, 16(): S2. DOI:10.1186/1471-2105-16-s10-s2 .
[32]
KIMJ, WANGY, TAKAGIT, et al. Overview of Genia Event Task in BioNLP shared Task 2011 [DB/OL].[2021-08-05]. https://dl.acm.org/doi/pdf/10.5555/2107691.2107693.
[33]
PYYSALOS, OHTAT, MIWAM, et al. Event extraction across multiple levels of biological organization [J]. Bioinformatics, 2012, 28(18): i575-i581. DOI:10.1093/bioinformatics/bts407 .
[34]
MIWAM, ANANIADOUS. Adaptable, high recall, event extraction system with minimal configuration [J]. BMC Bioinformatics, 2015, 16(10): 1-11. DOI:10.1186/1471-2105-16-S10-S7 .
[35]
BJÖRNEJ, SALAKOSKIT. Biomedical event extraction using convolutional neural networks and dependency parsing [C]//Proceedings of the BioNLP 2018 Workshop. Stroudsburg: Association for Computational Linguistics, 2018: 98-108. DOI:10.18653/v1/w18-2311 .
[36]
LIL S, LIUY, QINM Y. Extracting biomedical events with parallel multi-pooling convolutional neural networks[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020, 17(2): 599-607. DOI:10.1109/TCBB.2018.2868078 .
[37]
ZHUL, ZHENGH R. Biomedical event extraction with a novel combination strategy based on hybrid deep neural networks [J]. BMC Bioinformatics, 2020, 21(1): 1-12. DOI:10.1186/s12859-020-3376-2 .
[38]
CHENY B, XUL H, LIUK, et al. Event extraction via dynamic multi-pooling convolutional neural networks [C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Stroudsburg: Association for Computational Linguistics, 2015: 167-176. DOI:10.3115/v1/p15-1017 .