CollaboNet: collaboration of deep neural networks for biomedical named entity recognition

By WonJin Yoon, Chan Ho So, Jinhyuk Lee, Jaewoo Kang. 2018

147 citations recorded by the source corpus.

Finding biomedical named entities is one of the most essential tasks in biomedical text mining. Recently, deep learning-based approaches have been applied to biomedical named entity recognition (BioNER) and showed promising results. However, as deep learning approaches need an abundant amount of training data, a lack of data can hinder performance. BioNER datasets are scarce resources and each dataset covers only a small subset of entity types. Furthermore, many bio entities are polysemous, which is one of the major obstacles in named entity recognition. To address the lack of data and the entity type misclassification problem, we propose CollaboNet which utilizes a combination of multiple NER models. In CollaboNet, models trained on a different dataset are connected to each other so that a target model obtains information from other collaborator models to reduce false positives. Every model is an expert on their target entity type and takes turns serving as a target and a collaborator model during training time. The experimental results show that CollaboNet can be used to greatly reduce the number of false positives and misclassified entities including polysemous words. CollaboNet achieved state-of-the-art performance in terms of precision, recall and F1 score. We demonstrated the benefits of combining multiple models for BioNER. Our model has successfully reduced the number of misclassified entities and improved the performance by leveraging multiple datasets annotated for different entity types. Given the state-of-the-art performance of our model, we believe that CollaboNet can improve the accuracy of downstream biomedical text mining applications such as bio-entity relation extraction.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Natural Language Processing

Citations in the corpus

SciBERT: A Pretrained Language Model for Scientific Text (2019, methodology): “The SOTA model for JNLPBA is a BiLSTM-CRF ensemble trained on multiple NER datasets not just JNLPBA (Yoon et al., 2018).”
BioBERT: a pre-trained biomedical language representation model for biomedical text mining (2019, methodology): “…the BioBERT (and BERT) architecture does not use CRF. Note that while previous works in biomedical NER often use word embeddings trained on PubMed or PMC (Habibi et al. , 2017; Yoon et al. , 2018), we do not need to use them as BioBERT learns WordPiece embeddings from scratch while pre-training.”
BERT: A Review of Applications in Natural Language Processing and Understanding (2021, methodology): “The authors of the model used three common tasks to assess the performance of the model: named entity recognition (NER [89]), relation extraction (REL), and answering a question (QA [67]).”
SciBERT: Pretrained Contextualized Embeddings for Scientific Text (2019, unknown): “SCIBERT performs slightly worse than the SOTA on JNLPBA (Yoon et al., 2018), PubMed 20K RCT (Jin and Szolovits, 2018), and GENIA (Nguyen and Verspoor, 2019).”
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets (2019, unknown): “(Chen et al., 2019); BC5CDR-disease, BC5CDR-chem (Yoon et al., 2018); ShARe/CLEFE (Leaman et al., 2015); DDI (Zhang et al., 2018).”