Multiple-level biomedical event trigger recognition with transfer learning

A biomedical event extraction method based on fine-grained and attention mechanism

Background

Biomedical event extraction is a fundamental task in biomedical text mining, which provides inspiration for medicine research and disease prevention. Biomedical events include simple events and complex events. Existing biomedical event extraction methods usually deal with simple events and complex events uniformly, and the performance of complex event extraction is relatively low.

Results

In this paper, we propose a fine-grained Bidirectional Long Short Term Memory method for biomedical event extraction, which designs different argument detection models for simple and complex events respectively. In addition, multi-level attention is designed to improve the performance of complex event extraction, and sentence embeddings are integrated to obtain sentence level information which can resolve the ambiguities for some types of events. Our method achieves state-of-the-art performance on the commonly used dataset Multi-Level Event Extraction.

Conclusions

The sentence embeddings enrich the global sentence-level information. The fine-grained argument detection model improves the performance of complex biomedical event extraction. Furthermore, the multi-level attention mechanism enhances the interactions among relevant arguments. The experimental results demonstrate the effectiveness of the proposed method for biomedical event extraction.

AT-NeuroEAE: A Joint Extraction Model of Events With Attributes for Research Sharing-Oriented Neuroimaging Provenance Construction

Provenances are a research focus of neuroimaging resources sharing. An amount of work has been done to construct high-quality neuroimaging provenances in a standardized and convenient way. However, besides existing processed-based provenance extraction methods, open research sharing in computational neuroscience still needs one way to extract provenance information from rapidly growing published resources. This paper proposes a literature mining-based approach for research sharing-oriented neuroimaging provenance construction. A group of neuroimaging event-containing attributes are defined to model the whole process of neuroimaging researches, and a joint extraction model based on deep adversarial learning, called AT-NeuroEAE, is proposed to realize the event extraction in a few-shot learning scenario. Finally, a group of experiments were performed on the real data set from the journal PLOS ONE. Experimental results show that the proposed method provides a practical approach to quickly collect research information for neuroimaging provenance construction oriented to open research sharing.

Chinese Emergency Event Recognition Using Conv-RDBiGRU Model

In view of the weak generalization of traditional event recognition methods, the limitation of dependence on field knowledge of expert, the longer train time of deep neural network, and the problem of gradient dispersion, the neural network joint model, Conv-RDBiGRU, integrated residual structure was proposed. Firstly, text corpus is preprocessed by word segmentation and stop words processing and uses word embedding to form the matrix of word vectors. Then, local semantic features are extracted through convolution operation, and deep context semantic features are extracted through RDBiGRU. Finally, the learned features are activated by softmax function and the recognition results are output. The novelty of work is that we integrate residual structure into recurrent neural network and combine these methods and field of application. The simulation results show that this method improves precision and recall of Chinese emergency event recognition, and the F-value is better than other methods.