A novel joint biomedical event extraction framework via two-level modeling of documents

Abstract With the rapid development of information technology, the amount of textual data generated in biomedical field becomes larger and larger. Biomedical event extraction, which is a fundamental information extraction task, has gained a growing interest in biomedical community. Although researchers have proposed various approaches to this task, the performance is still undesirable since previous approaches fail to model biomedical documents effectively. In this paper, we propose an end-to-end framework for document-level joint biomedical event extraction. To better capture the complex relationships among contexts in biomedical documents, a two-level modeling approach is introduced for biomedical documents. More specifically, the dependency-based GCN and hypergraph are used to model local context and global context in each biomedical document, respectively. In addition, a fine-grained interaction mechanism is proposed to model effectively the interaction between local and global contexts to learn better contextualized representations for biomedical event extraction. Comprehensive experiments on two widely used datasets are conducted and the results demonstrate the effectiveness of the proposed framework over state-of-the-art methods.

[1]  Bryan Hooi,et al.  Structural Patterns and Generative Models of Real-world Hypergraphs , 2020, KDD.

[2]  Sampo Pyysalo,et al.  Event extraction across multiple levels of biological organization , 2012, Bioinform..

[3]  Ka-Chun Wong,et al.  Context awareness and embedding for biomedical event extraction , 2019, Bioinform..

[4]  Bernhard Schölkopf,et al.  Learning with Hypergraphs: Clustering, Classification, and Embedding , 2006, NIPS.

[5]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[6]  Jian Wang,et al.  Biomedical event extraction based on GRU integrating attention mechanism , 2018, BMC Bioinformatics.

[7]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[8]  Ligang Wu,et al.  Dissipativity-Based Filtering for Switched Genetic Regulatory Networks with Stochastic Disturbances and Time-Varying Delays , 2021, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[9]  Lvxing Zhu,et al.  Biomedical event extraction with a novel combination strategy based on hybrid deep neural networks , 2020, BMC Bioinformatics.

[10]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[11]  Jari Björne,et al.  EXTRACTING CONTEXTUALIZED COMPLEX BIOLOGICAL EVENTS WITH RICH GRAPH‐BASED FEATURE SETS , 2011, Comput. Intell..

[12]  Hongfei Lin,et al.  A multiple distributed representation method based on neural network for biomedical event extraction , 2017, BMC Medical Informatics and Decision Making.

[13]  David Sontag,et al.  Learning a Health Knowledge Graph from Electronic Medical Records , 2017, Scientific Reports.

[14]  Yue Gao,et al.  Hypergraph-Induced Convolutional Networks for Visual Classification , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Timo Aila,et al.  Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning , 2016, ArXiv.

[16]  Shao-Wu Zhang,et al.  NPBSS: a new PacBio sequencing simulator for generating the continuous long reads with an empirical model , 2018, BMC Bioinformatics.

[17]  Sophia Ananiadou,et al.  Event-based text mining for biology and functional genomics , 2014, Briefings in functional genomics.

[18]  Jari Björne,et al.  TEES 2.2: Biomedical Event Extraction for Diverse Corpora , 2015, BMC Bioinformatics.

[19]  Yubo Zhang,et al.  Hypergraph Label Propagation Network , 2020, AAAI.

[20]  Sampo Pyysalo,et al.  Wide coverage biomedical event extraction using multiple partially overlapping corpora , 2013, BMC Bioinformatics.

[21]  Kevin Gimpel,et al.  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations , 2019, ICLR.

[22]  Yue Gao,et al.  Hypergraph Neural Networks , 2018, AAAI.

[23]  Zhifang Sui,et al.  Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction , 2018, AAAI.