Disease named entity recognition by combining conditional random fields and bidirectional recurrent neural networks

Abstract

The recognition of disease and chemical named entities in scientific articles is a very important subtask in information extraction in the biomedical domain. Due to the diversity and complexity of disease names, the recognition of named entities of diseases is rather tougher than those of chemical names. Although there are some remarkable chemical named entity recognition systems available online such as ChemSpot and tmChem, the publicly available recognition systems of disease named entities are rare. This article presents a system for disease named entity recognition (DNER) and normalization. First, two separate DNER models are developed. One is based on conditional random fields model with a rule-based post-processing module. The other one is based on the bidirectional recurrent neural networks. Then the named entities recognized by each of the DNER model are fed into a support vector machine classifier for combining results. Finally, each recognized disease named entity is normalized to a medical subject heading disease name by using a vector space model based method. Experimental results show that using 1000 PubMed abstracts for training, our proposed system achieves an F1-measure of 0.8428 at the mention level and 0.7804 at the concept level, respectively, on the testing data of the chemical-disease relation task in BioCreative V.Database URL: http://219.223.252.210:8080/SS/cdr.html

A Survey on Deep Learning for Named Entity Recognition

“…When incorporating common priori knowledge (e.g., gazetteers and POS), the resulting system outperforms the baseline using only word-level representations. In the BiLSTM-CRF model by Huang Wei et al [108] presented a CRF-based neural system for recognizing and normalizing disease names. This system employs rich features in addition to word embeddings, including words, POS tags, chunking, and word shape features (e.g., dictionary and morphological features).…”

Conditional Random Fields for Biomedical Named Entity Recognition Revisited

“…Nayel et al [16] proposed a deep learning based approach to improve multi-word BioNER extraction. Wei et al [17], developed an ensemble-based system for Disease-NER. At the base level, they built CRF with a rulebased post-processing system and Bi-RNN based system.…”

A Low-Cost Named Entity Recognition Research Based on Active Learning

“…At the same time, driven by the demand of natural language processing in various fields, the recognition objective of NER has also evolved from the initial person name, location name, and time to the words or phrases with special meanings in the recognition text. Researchers have also carried out NER research mainly for specific domain entities, such as fishery data [16], dietary data [17], and Chinese legal documents data [18]. CRF model is one of the most popular ones.…”