Towards reliable named entity recognition in the biomedical domain

Abstract Motivation Automatic biomedical named entity recognition (BioNER) is a key task in biomedical information extraction. For some time, state-of-the-art BioNER has been dominated by machine learning methods, particularly conditional random fields (CRFs), with a recent focus on deep learning. However, recent work has suggested that the high performance of CRFs for BioNER may not generalize to corpora other than the one it was trained on. In our analysis, we find that a popular deep learning-based approach to BioNER, known as bidirectional long short-term memory network-conditional random field (BiLSTM-CRF), is correspondingly poor at generalizing. To address this, we evaluate three modifications of BiLSTM-CRF for BioNER to improve generalization: improved regularization via variational dropout, transfer learning and multi-task learning. Results We measure the effect that each strategy has when training/testing on the same corpus (‘in-corpus’ performance) and when training on one corpus and evaluating on another (‘out-of-corpus’ performance), our measure of the model’s ability to generalize. We found that variational dropout improves out-of-corpus performance by an average of 4.62%, transfer learning by 6.48% and multi-task learning by 8.42%. The maximal increase we identified combines multi-task learning and variational dropout, which boosts out-of-corpus performance by 10.75%. Furthermore, we make available a new open-source tool, called Saber that implements our best BioNER models. Availability and implementation Source code for our biomedical IE tool is available at https://github.com/BaderLab/saber. Corpora and other resources used in this study are available at https://github.com/BaderLab/Towards-reliable-BioNER. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Towards reliable named entity recognition in the biomedical domain

10.1101/526244 ◽

2019 ◽

Cited By ~ 2

Author(s):

John Giorgi ◽

Gary Bader

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

High Performance ◽

Short Term Memory ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Entity Recognition ◽

Maximal Increase ◽

Named Entity ◽

Task Learning

Motivation: Automatic biomedical named entity recognition (BioNER) is a key task in biomedical information extraction (IE). For some time, state-of-the-art BioNER has been dominated by machine learning methods, particularly conditional random fields (CRFs), with a recent focus on deep learning. However, recent work has suggested that the high performance of CRFs for BioNER may not generalize to corpora other than the one it was trained on. In our analysis, we find that a popular deep learning-based approach to BioNER, known as bidirectional long short-term memory network-conditional random field (BiLSTM-CRF), is correspondingly poor at generalizing - often dramatically overfitting the corpus it was trained on. To address this, we evaluate three modifications of BiLSTM-CRF for BioNER to alleviate overfitting and improve generalization: improved regularization via variational dropout, transfer learning, and multi-task learning. Results: We measure the effect that each strategy has when training/testing on the same corpus ("in-corpus" performance) and when training on one corpus and evaluating on another ("out-of-corpus" performance), our measure of the models ability to generalize. We found that variational dropout improves out-of-corpus performance by an average of 4.62%, transfer learning by 6.48% and multi-task learning by 8.42%. The maximal increase we identified combines multi-task learning and variational dropout, which boosts out-of-corpus performance by 10.75%. Furthermore, we make available a new open-source tool, called Saber, that implements our best BioNER models. Availability: Source code for our biomedical IE tool is available at https://github.com/BaderLab/saber. Corpora and other resources used in this study are available at https://github.com/BaderLab/Towards- reliable-BioNER.

Download Full-text

Transfer learning for biomedical named entity recognition with neural networks

10.1101/262790 ◽

2018 ◽

Author(s):

John M Giorgi ◽

Gary D Bader

Keyword(s):

Transfer Learning ◽

Short Term Memory ◽

State Of The Art ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Biomedical Literature ◽

Entity Recognition ◽

Supplementary Information ◽

Link Type ◽

Training Examples

AbstractMotivationThe explosive increase of biomedical literature has made information extraction an increasingly important tool for biomedical research. A fundamental task is the recognition of biomedical named entities in text (BNER) such as genes/proteins, diseases, and species. Recently, a domain-independent method based on deep learning and statistical word embeddings, called long short-term memory network-conditional random field (LSTM-CRF), has been shown to outperform state-of-the-art entity-specific BNER tools. However, this method is dependent on gold-standard corpora (GSCs) consisting of hand-labeled entities, which tend to be small but highly reliable. An alternative to GSCs are silver-standard corpora (SSCs), which are generated by harmonizing the annotations made by several automatic annotation systems. SSCs typically contain more noise than GSCs but have the advantage of containing many more training examples. Ideally, these corpora could be combined to achieve the benefits of both, which is an opportunity for transfer learning. In this work, we analyze to what extent transfer learning improves upon state-of-the-art results for BNER.ResultsWe demonstrate that transferring a deep neural network (DNN) trained on a large, noisy SSC to a smaller, but more reliable GSC significantly improves upon state-of-the-art results for BNER. Compared to a state-of-the-art baseline evaluated on 23 GSCs covering four different entity classes, transfer learning results in an average reduction in error of approximately 11%. We found transfer learning to be especially beneficial for target data sets with a small number of labels (approximately 6000 or less).Availability and implementationSource code for the LSTM-CRF is available at https://github.com/Franck-Dernoncourt/NeuroNER/ and links to the corpora are available at https://github.com/BaderLab/Transfer-Learning-BNER-Bioinformatics-2018/[email protected] informationSupplementary data are available at Bioinformatics online.

Download Full-text

Hierarchical shared transfer learning for biomedical named entity recognition

BMC Bioinformatics ◽

10.1186/s12859-021-04551-4 ◽

2022 ◽

Vol 23 (1) ◽

Author(s):

Zhaoying Chai ◽

Han Jin ◽

Shenghui Shi ◽

Siyan Zhan ◽

Lin Zhuo ◽

...

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Medical Information ◽

Named Entity Recognition ◽

Fine Tuning ◽

Entity Recognition ◽

Single Task ◽

Named Entity ◽

Task Learning ◽

Biomedical Named Entity Recognition

Abstract Background Biomedical named entity recognition (BioNER) is a basic and important medical information extraction task to extract medical entities with special meaning from medical texts. In recent years, deep learning has become the main research direction of BioNER due to its excellent data-driven context coding ability. However, in BioNER task, deep learning has the problem of poor generalization and instability. Results we propose the hierarchical shared transfer learning, which combines multi-task learning and fine-tuning, and realizes the multi-level information fusion between the underlying entity features and the upper data features. We select 14 datasets containing 4 types of entities for training and evaluate the model. The experimental results showed that the F1-scores of the five gold standard datasets BC5CDR-chemical, BC5CDR-disease, BC2GM, BC4CHEMD, NCBI-disease and LINNAEUS were increased by 0.57, 0.90, 0.42, 0.77, 0.98 and − 2.16 compared to the single-task XLNet-CRF model. BC5CDR-chemical, BC5CDR-disease and BC4CHEMD achieved state-of-the-art results.The reasons why LINNAEUS’s multi-task results are lower than single-task results are discussed at the dataset level. Conclusion Compared with using multi-task learning and fine-tuning alone, the model has more accurate recognition ability of medical entities, and has higher generalization and stability.

Download Full-text

Deep Learning-Based Named Entity Recognition and Knowledge Graph Construction for Geological Hazards

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9010015 ◽

2019 ◽

Vol 9 (1) ◽

pp. 15 ◽

Cited By ~ 2

Author(s):

Runyu Fan ◽

Lizhe Wang ◽

Jining Yan ◽

Weijing Song ◽

Yingqian Zhu ◽

...

Keyword(s):

Deep Learning ◽

Large Scale ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Entity Recognition ◽

Knowledge Graph ◽

Geological Hazard ◽

Geological Hazards ◽

Named Entity ◽

Corpus Construction

Constructing a knowledge graph of geological hazards literature can facilitate the reuse of geological hazards literature and provide a reference for geological hazard governance. Named entity recognition (NER), as a core technology for constructing a geological hazard knowledge graph, has to face the challenges that named entities in geological hazard literature are diverse in form, ambiguous in semantics, and uncertain in context. This can introduce difficulties in designing practical features during the NER classification. To address the above problem, this paper proposes a deep learning-based NER model; namely, the deep, multi-branch BiGRU-CRF model, which combines a multi-branch bidirectional gated recurrent unit (BiGRU) layer and a conditional random field (CRF) model. In an end-to-end and supervised process, the proposed model automatically learns and transforms features by a multi-branch bidirectional GRU layer and enhances the output with a CRF layer. Besides the deep, multi-branch BiGRU-CRF model, we also proposed a pattern-based corpus construction method to construct the corpus needed for the deep, multi-branch BiGRU-CRF model. Experimental results indicated the proposed deep, multi-branch BiGRU-CRF model outperformed state-of-the-art models. The proposed deep, multi-branch BiGRU-CRF model constructed a large-scale geological hazard literature knowledge graph containing 34,457 entities nodes and 84,561 relations.

Download Full-text

CWPC_BiAtt: Character–Word–Position Combined BiLSTM-Attention for Chinese Named Entity Recognition

Information ◽

10.3390/info11010045 ◽

2020 ◽

Vol 11 (1) ◽

pp. 45 ◽

Cited By ~ 1

Author(s):

Shardrom Johnson ◽

Sherlock Shen ◽

Yuanchen Liu

Keyword(s):

Language Processing ◽

Short Term Memory ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Attention Mechanism ◽

Entity Recognition ◽

Position Information ◽

Named Entity ◽

Pos Tagging ◽

Word Position

Usually taken as linguistic features by Part-Of-Speech (POS) tagging, Named Entity Recognition (NER) is a major task in Natural Language Processing (NLP). In this paper, we put forward a new comprehensive-embedding, considering three aspects, namely character-embedding, word-embedding, and pos-embedding stitched in the order we give, and thus get their dependencies, based on which we propose a new Character–Word–Position Combined BiLSTM-Attention (CWPC_BiAtt) for the Chinese NER task. Comprehensive-embedding via the Bidirectional Llong Short-Term Memory (BiLSTM) layer can get the connection between the historical and future information, and then employ the attention mechanism to capture the connection between the content of the sentence at the current position and that at any location. Finally, we utilize Conditional Random Field (CRF) to decode the entire tagging sequence. Experiments show that CWPC_BiAtt model we proposed is well qualified for the NER task on Microsoft Research Asia (MSRA) dataset and Weibo NER corpus. A high precision and recall were obtained, which verified the stability of the model. Position-embedding in comprehensive-embedding can compensate for attention-mechanism to provide position information for the disordered sequence, which shows that comprehensive-embedding has completeness. Looking at the entire model, our proposed CWPC_BiAtt has three distinct characteristics: completeness, simplicity, and stability. Our proposed CWPC_BiAtt model achieved the highest F-score, achieving the state-of-the-art performance in the MSRA dataset and Weibo NER corpus.

Download Full-text

Information Extraction from Electronic Medical Records Using Multitask Recurrent Neural Network with Contextual Word Embedding

Applied Sciences ◽

10.3390/app9183658 ◽

2019 ◽

Vol 9 (18) ◽

pp. 3658 ◽

Cited By ~ 6

Author(s):

Jianliang Yang ◽

Yuenan Liu ◽

Minghui Qian ◽

Chenghua Guan ◽

Xiangfei Yuan

Keyword(s):

Electronic Medical Records ◽

Medical Records ◽

Large Scale ◽

Short Term Memory ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Recognition Task ◽

Entity Recognition ◽

Language Models ◽

Named Entity

Clinical named entity recognition is an essential task for humans to analyze large-scale electronic medical records efficiently. Traditional rule-based solutions need considerable human effort to build rules and dictionaries; machine learning-based solutions need laborious feature engineering. For the moment, deep learning solutions like Long Short-term Memory with Conditional Random Field (LSTM–CRF) achieved considerable performance in many datasets. In this paper, we developed a multitask attention-based bidirectional LSTM–CRF (Att-biLSTM–CRF) model with pretrained Embeddings from Language Models (ELMo) in order to achieve better performance. In the multitask system, an additional task named entity discovery was designed to enhance the model’s perception of unknown entities. Experiments were conducted on the 2010 Informatics for Integrating Biology & the Bedside/Veterans Affairs (I2B2/VA) dataset. Experimental results show that our model outperforms the state-of-the-art solution both on the single model and ensemble model. Our work proposes an approach to improve the recall in the clinical named entity recognition task based on the multitask mechanism.

Download Full-text

Dataset-aware multi-task learning approaches for biomedical named entity recognition

Bioinformatics ◽

10.1093/bioinformatics/btaa515 ◽

2020 ◽

Vol 36 (15) ◽

pp. 4331-4338

Author(s):

Mei Zuo ◽

Yang Zhang

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

State Of The Art ◽

Named Entity Recognition ◽

Entity Recognition ◽

Quality Data ◽

Supplementary Information ◽

Named Entity ◽

Task Learning ◽

Biomedical Named Entity Recognition

Abstract Motivation Named entity recognition is a critical and fundamental task for biomedical text mining. Recently, researchers have focused on exploiting deep neural networks for biomedical named entity recognition (Bio-NER). The performance of deep neural networks on a single dataset mostly depends on data quality and quantity while high-quality data tends to be limited in size. To alleviate task-specific data limitation, some studies explored the multi-task learning (MTL) for Bio-NER and achieved state-of-the-art performance. However, these MTL methods did not make full use of information from various datasets of Bio-NER. The performance of state-of-the-art MTL method was significantly limited by the number of training datasets. Results We propose two dataset-aware MTL approaches for Bio-NER which jointly train all models for numerous Bio-NER datasets, thus each of these models could discriminatively exploit information from all of related training datasets. Both of our two approaches achieve substantially better performance compared with the state-of-the-art MTL method on 14 out of 15 Bio-NER datasets. Furthermore, we implemented our approaches by incorporating Bio-NER and biomedical part-of-speech (POS) tagging datasets. The results verify Bio-NER and POS can significantly enhance one another. Availability and implementation Our source code is available at https://github.com/zmmzGitHub/MTL-BC-LBC-BioNER and all datasets are publicly available at https://github.com/cambridgeltl/MTL-Bioinformatics-2016. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Pengenalan Entitas Bernama Otomatis untuk Bahasa Indonesia dengan Pendekatan Pembelajaran Mesin

10.31227/osf.io/vud2p ◽

2018 ◽

Cited By ~ 2

Author(s):

Yudi Wibisono ◽

Masayu Leylia Khodra

Keyword(s):

Short Term Memory ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Entity Recognition ◽

Short Term ◽

Term Memory ◽

Named Entity ◽

Long Short Term Memory ◽

F Measure ◽

Bahasa Indonesia

Pengenalan entitas bernama (named-entity recognition atau NER) adalah proses otomatis mengekstraksi entitas bernama yang dianggap penting di dalam sebuah teks dan menentukan kategorinya ke dalam kategori terdefinisi. Sebagai contoh, untuk teks berita, NER dapat mengekstraksi nama orang, nama organisasi, dan nama lokasi. NER bermanfaat dalam berbagai aplikasi analisis teks, misalnya pencarian, sistem tanya jawab, peringkasan teks dan mesin penerjemah. Tantangan utama NER adalah penanganan ambiguitas makna karena konteks kata pada kalimat, misalnya kata “Cendana” dapat merupakan nama lokasi (Jalan Cendana), atau nama organisasi (Keluarga Cendana), atau nama tanaman. Tantangan lainnya adalah penentuan batas entitas, misalnya “[Istora Senayan] [Jakarta]”. Berbagai kakas NER telah dikembangkan untuk berbagai bahasa terutama Bahasa Inggris dengan kinerja yang baik, tetapi kakas NER bahasa Indonesia masih memiliki kinerja yang belum baik. Makalah ini membahas pendekatan berbasis pembelajaran mesin untuk menghasilkan model NER bahasa Indonesia. Pendekatan ini sangat bergantung pada korpus yang menjadi sumber belajar, dan teknik pembelajaran mesin yang digunakan. Teknik yang akan digunakan adalah LSTM - CRF (Long Short Term Memory – Conditional Random Field). Hasil terbaik (F-measure = 0.72) didapatkan dengan menggunakan word embedding GloVe Wikipedia Bahasa Indonesia.

Download Full-text

Biomedical named entity recognition using deep neural networks with contextual information

BMC Bioinformatics ◽

10.1186/s12859-019-3321-4 ◽

2019 ◽

Vol 20 (1) ◽

Cited By ~ 8

Author(s):

Hyejin Cho ◽

Hyunju Lee

Keyword(s):

Deep Learning ◽

Short Term Memory ◽

Contextual Information ◽

Named Entity Recognition ◽

Entity Recognition ◽

Learning Approaches ◽

Short Term ◽

Term Memory ◽

Named Entity ◽

Long Short Term Memory

Abstract Background In biomedical text mining, named entity recognition (NER) is an important task used to extract information from biomedical articles. Previously proposed methods for NER are dictionary- or rule-based methods and machine learning approaches. However, these traditional approaches are heavily reliant on large-scale dictionaries, target-specific rules, or well-constructed corpora. These methods to NER have been superseded by the deep learning-based approach that is independent of hand-crafted features. However, although such methods of NER employ additional conditional random fields (CRF) to capture important correlations between neighboring labels, they often do not incorporate all the contextual information from text into the deep learning layers. Results We propose herein an NER system for biomedical entities by incorporating n-grams with bi-directional long short-term memory (BiLSTM) and CRF; this system is referred to as a contextual long short-term memory networks with CRF (CLSTM). We assess the CLSTM model on three corpora: the disease corpus of the National Center for Biotechnology Information (NCBI), the BioCreative II Gene Mention corpus (GM), and the BioCreative V Chemical Disease Relation corpus (CDR). Our framework was compared with several deep learning approaches, such as BiLSTM, BiLSTM with CRF, GRAM-CNN, and BERT. On the NCBI corpus, our model recorded an F-score of 85.68% for the NER of diseases, showing an improvement of 1.50% over previous methods. Moreover, although BERT used transfer learning by incorporating more than 2.5 billion words, our system showed similar performance with BERT with an F-scores of 81.44% for gene NER on the GM corpus and a outperformed F-score of 86.44% for the NER of chemicals and diseases on the CDR corpus. We conclude that our method significantly improves performance on biomedical NER tasks. Conclusion The proposed approach is robust in recognizing biological entities in text.

Download Full-text

Ontology-Based Healthcare Named Entity Recognition from Twitter Messages Using a Recurrent Neural Network Approach

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16193628 ◽

2019 ◽

Vol 16 (19) ◽

pp. 3628 ◽

Cited By ~ 5

Author(s):

Erdenebileg Batbaatar ◽

Keun Ho Ryu

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Adverse Drug Events ◽

Viterbi Algorithm ◽

Short Term Memory ◽

Conditional Random Field ◽

Named Entity Recognition ◽

Entity Recognition ◽

Named Entity ◽

Health Related

Named Entity Recognition (NER) in the healthcare domain involves identifying and categorizing disease, drugs, and symptoms for biosurveillance, extracting their related properties and activities, and identifying adverse drug events appearing in texts. These tasks are important challenges in healthcare. Analyzing user messages in social media networks such as Twitter can provide opportunities to detect and manage public health events. Twitter provides a broad range of short messages that contain interesting information for information extraction. In this paper, we present a Health-Related Named Entity Recognition (HNER) task using healthcare-domain ontology that can recognize health-related entities from large numbers of user messages from Twitter. For this task, we employ a deep learning architecture which is based on a recurrent neural network (RNN) with little feature engineering. To achieve our goal, we collected a large number of Twitter messages containing health-related information, and detected biomedical entities from the Unified Medical Language System (UMLS). A bidirectional long short-term memory (BiLSTM) model learned rich context information, and a convolutional neural network (CNN) was used to produce character-level features. The conditional random field (CRF) model predicted a sequence of labels that corresponded to a sequence of inputs, and the Viterbi algorithm was used to detect health-related entities from Twitter messages. We provide comprehensive results giving valuable insights for identifying medical entities in Twitter for various applications. The BiLSTM-CRF model achieved a precision of 93.99%, recall of 73.31%, and F1-score of 81.77% for disease or syndrome HNER; a precision of 90.83%, recall of 81.98%, and F1-score of 87.52% for sign or symptom HNER; and a precision of 94.85%, recall of 73.47%, and F1-score of 84.51% for pharmacologic substance named entities. The ontology-based manual annotation results show that it is possible to perform high-quality annotation despite the complexity of medical terminology and the lack of context in tweets.

Download Full-text