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

@article{Yoon2019CollaboNetCO,
  title={CollaboNet: collaboration of deep neural networks for biomedical named entity recognition},
  author={Wonjin Yoon and Chan Ho So and Jinhyuk Lee and Jaewoo Kang},
  journal={BMC Bioinformatics},
  year={2019},
  volume={20}
}
BackgroundFinding biomedical named entities is one of the most essential tasks in biomedical text mining. [...] Key Method 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…Expand
Multitask learning for biomedical named entity recognition with cross-sharing structure
TLDR
A novel multi-task model for BioNER with the cross-sharing structure to improve the performance of multi- task models is proposed and found the model outperformed the others on datasets of gene, protein, disease categories. Expand
Comparison of Named Entity Recognition models based on Neural Network in Biomedical
The need of automated information extraction increases with the increase in biomedical text. Named entity recognition is one of the core tasks in automatic information extraction. Performing namedExpand
Improving biomedical named entity recognition with syntactic information
TLDR
The experimental results on six English benchmark datasets demonstrate that auto-processed syntactic information can be a useful resource for BioNER and the method with KVMN can appropriately leverage such information to improve model performance. Expand
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information
  • Yiqi Tong, Yidong Chen, Xiaodong Shi
  • Computer Science
  • FINDINGS
  • 2021
TLDR
This paper proposes a method that simultaneously utilize the latent multi-granularity information in the dataset that produces better performance over the BioBERT baseline and can get more than 3% improvements of F1score in low-resource scenarios. Expand
Deep learning methods for biomedical named entity recognition: a survey and qualitative comparison.
  • Bosheng Song, Fen Li, Yuansheng Liu, Xiangxiang Zeng
  • Medicine
  • Briefings in bioinformatics
  • 2021
TLDR
This review comprehensively summarize deep learning-based methods for BioNER and datasets used in training and testing, and discusses the future development and opportunities of BioNER methods. Expand
Analyzing the Effect of Multi-task Learning for Biomedical Named Entity Recognition
TLDR
This study performs an extensive analysis to understand the transferability between different biomedical entity datasets and proposes combining transfer learning and multi-task learning to improve the performance of biomedical named entity recognition systems, which is not applied before. Expand
BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger
TLDR
This work introduces BioNerFlair, a method to train models for biomedical named entity recognition using Flair plus GloVe embeddings and Bidirectional LSTM-CRF based sequence tagger, which outperforms previous state-of-the-art models. Expand
Combinatorial feature embedding based on CNN and LSTM for biomedical named entity recognition
TLDR
A deep learning NER model that effectively represents biomedical word tokens through the design of a combinatorial feature embedding, based on Bidirectional Long Short-Term Memory with Conditional Random Field and enhanced by integrating two different character-level representations extracted from a Convolutional Neural Network and bi-LSTM. Expand
BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition
TLDR
Biomedical ALBERT (A Lite Bidirectional Encoder Representations from Transformers for Biomedical Text Mining) is proposed, an effective domain-specific language model trained on large-scale biomedical corpora designed to capture biomedical context-dependent NER. Expand
Distantly Supervised Biomedical Named Entity Recognition with Dictionary Expansion
TLDR
Experimental results show that AutoBioNER achieves the best performance among the methods that only use dictionaries with no additional human effort on BioNER benchmark datasets, and it is demonstrated that the dictionary expansion step plays an important role in the great performances. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 68 REFERENCES
Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning
TLDR
A multi-task learning framework for BioNER is proposed to collectively use the training data of different types of entities and improve the performance on each of them, achieving substantially better performance compared with state-of-the-art BioNER systems and baseline neural sequence labeling models. Expand
A neural network multi-task learning approach to biomedical named entity recognition
TLDR
The results show that, on average, the multi-task models produced better NER results than the single- task models trained on a single NER dataset, and it is found that Multi-task Learning is beneficial for small datasets. Expand
Deep learning with word embeddings improves biomedical named entity recognition
TLDR
This work shows that a completely generic method based on deep learning and statistical word embeddings [called long short‐term memory network‐conditional random field (LSTM‐CRF)] outperforms state‐of‐the‐art entity‐specific NER tools, and often by a large margin. Expand
NERBio: using selected word conjunctions, term normalization, and global patterns to improve biomedical named entity recognition
TLDR
Numerical normalization is applied, which solves the problem by replacing all numerals in a term with one representative numeral to help classify named entities and shows that numerical normalization can effectively reduce the number of redundant and unseen features. Expand
tmChem: a high performance approach for chemical named entity recognition and normalization
Chemical compounds and drugs are an important class of entities in biomedical research with great potential in a wide range of applications, including clinical medicine. Locating chemical namedExpand
DNorm: disease name normalization with pairwise learning to rank
TLDR
This article introduces the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM, a high-performing and mathematically principled framework for learning similarities between mentions and concept names directly from training data. Expand
Recurrent neural network models for disease name recognition using domain invariant features
TLDR
This work proposes various end-to-end recurrent neural network models for the tasks of disease name recognition and their classification into four pre-defined categories and utilizes convolution neural network in cascade of RNN to get character-based embedded features and employs it with word-embedded features in their model. Expand
Entity Linking for Biomedical Literature
TLDR
A novel unsupervised collective inference approach is proposed to address the EL problem in a new domain and is able to outperform a current state-of-the-art supervised approach that has been trained with a large amount of manually labeled data. Expand
Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task
TLDR
This task was found to be successful in engaging the text-mining research community, producing a large annotated corpus and improving the results of automatic disease recognition and CDR extraction. Expand
Annotating chemicals , diseases and their interactions in biomedical literature
Community-run formal evaluations and manually annotated text corpora are critically important for advancing biomedical text mining research. Recently in BioCreative V, a new challenge was organizedExpand
...
1
2
3
4
5
...