CRFVoter: gene and protein related object recognition using a conglomerate of CRF-based tools

Journal of Cheminformatics

Wahed Hemati¹  Alexander Mehler¹ 

[1] Text Technology Lab, Goethe-University Frankfurt;

关键词: BioCreative V.5;    Biomedical named entity recognition;    GPRO;    BioNLP;    Named entity recognition;    CRF;   

DOI  :  10.1186/s13321-019-0343-x

来源: DOAJ

【 摘 要 】

Abstract Background Gene and protein related objects are an important class of entities in biomedical research, whose identification and extraction from scientific articles is attracting increasing interest. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of gene and protein related objects. For this purpose, we transform the task as posed by BioCreative V.5 into a sequence labeling problem. We present a series of sequence labeling systems that we used and adapted in our experiments for solving this task. Our experiments show how to optimize the hyperparameters of the classifiers involved. To this end, we utilize various algorithms for hyperparameter optimization. Finally, we present CRFVoter, a two-stage application of Conditional Random Field (CRF) that integrates the optimized sequence labelers from our study into one ensemble classifier. Results We analyze the impact of hyperparameter optimization regarding named entity recognition in biomedical research and show that this optimization results in a performance increase of up to 60%. In our evaluation, our ensemble classifier based on multiple sequence labelers, called CRFVoter, outperforms each individual extractor’s performance. For the blinded test set provided by the BioCreative organizers, CRFVoter achieves an F-score of 75%, a recall of 71% and a precision of 80%. For the GPRO type 1 evaluation, CRFVoter achieves an F-Score of 73%, a recall of 70% and achieved the best precision (77%) among all task participants. Conclusion CRFVoter is effective when multiple sequence labeling systems are to be used and performs better then the individual systems collected by it.

【 授权许可】

Unknown