Integrating Dictionary Feature into A Deep Learning Model for Disease Named Entity Recognition

Abstract

In recent years, Deep Learning (DL) models are becoming important due to their demonstrated success at overcoming complex learning problems. DL models have been applied effectively for different Natural Language Processing (NLP) tasks such as part-of-Speech (PoS) tagging and Machine Translation (MT). Disease Named Entity Recognition (Disease-NER) is a crucial task which aims at extracting disease Named Entities (NEs) from text. In this paper, a DL model for Disease-NER using dictionary information is proposed and evaluated on National Center for Biotechnology Information (NCBI) disease corpus and BC5CDR dataset. Word embeddings trained over general domain texts as well as biomedical texts have been used to represent input to the proposed model. This study also compares two different Segment Representation (SR) schemes, namely IOB2 and IOBES for Disease-NER. The results illustrate that using dictionary information, pre-trained word embeddings, character embeddings and CRF with global score improves the performance of Disease-NER system.

A Multitask Learning Approach for Named Entity Recognition by Exploiting Sentence-Level Semantics Globally

“…Char-attention BiLSTM-CRF [54] 72.70 nested BiLSTM-CRF [55] 75.44 Dictionary BiLSTM-CRF [56] 71.99 BiLSTM-softmax [57] 73.60 LMs-BiLSTM-CRF [58] 74. OntoNotes 5.0 (English) dataset For the OntoNotes 5.0 (English) dataset, there have been an extensive number of investigations, as shown in Table 4.…”

“…JNLPBA (Medical) dataset On the biomedical JNLPBA dataset, we compared our model with previous state-of-the-art models, including [54,56], etc. With a BERT-based representation, our MTL model consistently outperformed all previous models, achieving the best results.…”

Multilingual enrichment of disease biomedical ontologies

“…Biomedical ontologies, like Orphanet (INSERM, 1999b), play an important role in many downstream tasks (Andronis et al, 2011;Li et al, 2015;Phan et al, 2017), especially in natural language processing (Maldonado et al, 2017;Nayel and Shashrekha, 2019). Today either the vast majority of these ontologies are only available in English or their restrictive licenses reduce the scope of their usage.…”