Dataset Information

Exploiting and assessing multi-source data for supervised biomedical named entity recognition.

ABSTRACT: Motivation:Recognition of biomedical entities from scientific text is a critical component of natural language processing and automated information extraction platforms. Modern named entity recognition approaches rely heavily on supervised machine learning techniques, which are critically dependent on annotated training corpora. These approaches have been shown to perform well when trained and tested on the same source. However, in such scenario, the performance and evaluation of these models may be optimistic, as such models may not necessarily generalize to independent corpora, resulting in potential non-optimal entity recognition for large-scale tagging of widely diverse articles in databases such as PubMed. Results:Here we aggregated published corpora for the recognition of biomolecular entities (such as genes, RNA, proteins, variants, drugs and metabolites), identified entity class overlap and performed leave-corpus-out cross validation strategy to test the efficiency of existing models. We demonstrate that accuracies of models trained on individual corpora decrease substantially for recognition of the same biomolecular entity classes in independent corpora. This behavior is possibly due to limited generalizability of entity-class-related features captured by individual corpora (model 'overtraining') which we investigated further at the orthographic level, as well as potential annotation standard differences. We show that the combined use of multi-source training corpora results in overall more generalizable models for named entity recognition, while achieving comparable individual performance. By performing learning-curve-based power analysis we further identified that performance is often not limited by the quantity of the annotated data. Availability and implementation:Compiled primary and secondary sources of the aggregated corpora are available on: https://github.com/dterg/biomedical_corpora/wiki and https://bitbucket.org/iAnalytica/bioner. Supplementary information:Supplementary data are available at Bioinformatics online.

SUBMITTER: Galea D

PROVIDER: S-EPMC6041968 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Named Entity Recognition (NER) is a key task in biomedical text mining. Accurate NER systems require task-specific, manually-annotated datasets, which are expensive to develop and thus limited in size. Since such datasets contain related but different information, an interesting question is whether it might be possible to use them together to improve NER performance. To investigate this, we develop supervised, multi-task, convolutional neural network models and apply them to a large number of varied existing biomedical named entity datasets. Additionally, we investigated the effect of dataset size on performance in both single- and multi-task settings.We present a single-task model for NER, a Multi-output multi-task model and a Dependent multi-task model. We apply the three models to 15 biomedical datasets containing multiple named entities including Anatomy, Chemical, Disease, Gene/Protein and Species. Each dataset represent a task. The results from the single-task model and the multi-task models are then compared for evidence of benefits from Multi-task Learning. With the Multi-output multi-task model we observed an average F-score improvement of 0.8% when compared to the single-task model from an average baseline of 78.4%. Although there was a significant drop in performance on one dataset, performance improves significantly for five datasets by up to 6.3%. For the Dependent multi-task model we observed an average improvement of 0.4% when compared to the single-task model. There were no significant drops in performance on any dataset, and performance improves significantly for six datasets by up to 1.1%. The dataset size experiments found that as dataset size decreased, the multi-output model's performance increased compared to the single-task model's. Using 50, 25 and 10% of the training data resulted in an average drop of approximately 3.4, 8 and 16.7% respectively for the single-task model but approximately 0.2, 3.0 and 9.8% for the multi-task model.Our results show that, on average, the multi-task models produced better NER results than the single-task models trained on a single NER dataset. We also found that Multi-task Learning is beneficial for small datasets. Across the various settings the improvements are significant, demonstrating the benefit of Multi-task Learning for this task.

Project description:MotivationThe 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 datasets 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/.Supplementary informationSupplementary data are available at Bioinformatics online.

Project description:Increased interest in the use of word embeddings, such as word representation, for biomedical named entity recognition (BioNER) has highlighted the need for evaluations that aid in selecting the best word embedding to be used. One common criterion for selecting a word embedding is the type of source from which it is generated; that is, general (e.g., Wikipedia, Common Crawl), or specific (e.g., biomedical literature). Using specific word embeddings for the BioNER task has been strongly recommended, considering that they have provided better coverage and semantic relationships among medical entities. To the best of our knowledge, most studies have focused on improving BioNER task performance by, on the one hand, combining several features extracted from the text (for instance, linguistic, morphological, character embedding, and word embedding itself) and, on the other, testing several state-of-the-art named entity recognition algorithms. The latter, however, do not pay great attention to the influence of the word embeddings, and do not facilitate observing their real impact on the BioNER task. For this reason, the present study evaluates three well-known NER algorithms (CRF, BiLSTM, BiLSTM-CRF) with respect to two corpora (DrugBank and MedLine) using two classic word embeddings, GloVe Common Crawl (of the general type) and Pyysalo PM + PMC (specific), as unique features. Furthermore, three contextualized word embeddings (ELMo, Pooled Flair, and Transformer) are compared in their general and specific versions. The aim is to determine whether general embeddings can perform better than specialized ones on the BioNER task. To this end, four experiments were designed. In the first, we set out to identify the combination of classic word embedding, NER algorithm, and corpus that results in the best performance. The second evaluated the effect of the size of the corpus on performance. The third assessed the semantic cohesiveness of the classic word embeddings and their correlation with respect to several gold standards; while the fourth evaluates the performance of general and specific contextualized word embeddings on the BioNER task. Results show that the classic general word embedding GloVe Common Crawl performed better in the DrugBank corpus, despite having less word coverage and a lower internal semantic relationship than the classic specific word embedding, Pyysalo PM + PMC; while in the contextualized word embeddings the best results are presented in the specific ones. We conclude, therefore, when using classic word embeddings as features on the BioNER task, the general ones could be considered a good option. On the other hand, when using contextualized word embeddings, the specific ones are the best option.

Project description:BACKGROUND:Biomedical named-entity recognition (BioNER) is widely modeled with conditional random fields (CRF) by regarding it as a sequence labeling problem. The CRF-based methods yield structured outputs of labels by imposing connectivity between the labels. Recent studies for BioNER have reported state-of-the-art performance by combining deep learning-based models (e.g., bidirectional Long Short-Term Memory) and CRF. The deep learning-based models in the CRF-based methods are dedicated to estimating individual labels, whereas the relationships between connected labels are described as static numbers; thereby, it is not allowed to timely reflect the context in generating the most plausible label-label transitions for a given input sentence. Regardless, correctly segmenting entity mentions in biomedical texts is challenging because the biomedical terms are often descriptive and long compared with general terms. Therefore, limiting the label-label transitions as static numbers is a bottleneck in the performance improvement of BioNER. RESULTS:We introduce DTranNER, a novel CRF-based framework incorporating a deep learning-based label-label transition model into BioNER. DTranNER uses two separate deep learning-based networks: Unary-Network and Pairwise-Network. The former is to model the input for determining individual labels, and the latter is to explore the context of the input for describing the label-label transitions. We performed experiments on five benchmark BioNER corpora. Compared with current state-of-the-art methods, DTranNER achieves the best F1-score of 84.56% beyond 84.40% on the BioCreative II gene mention (BC2GM) corpus, the best F1-score of 91.99% beyond 91.41% on the BioCreative IV chemical and drug (BC4CHEMD) corpus, the best F1-score of 94.16% beyond 93.44% on the chemical NER, the best F1-score of 87.22% beyond 86.56% on the disease NER of the BioCreative V chemical disease relation (BC5CDR) corpus, and a near-best F1-score of 88.62% on the NCBI-Disease corpus. CONCLUSIONS:Our results indicate that the incorporation of the deep learning-based label-label transition model provides distinctive contextual clues to enhance BioNER over the static transition model. We demonstrate that the proposed framework enables the dynamic transition model to adaptively explore the contextual relations between adjacent labels in a fine-grained way. We expect that our study can be a stepping stone for further prosperity of biomedical literature mining.

Project description:BackgroundSingle Nucleotide Polymorphisms, among other type of sequence variants, constitute key elements in genetic epidemiology and pharmacogenomics. While sequence data about genetic variation is found at databases such as dbSNP, clues about the functional and phenotypic consequences of the variations are generally found in biomedical literature. The identification of the relevant documents and the extraction of the information from them are hampered by the large size of literature databases and the lack of widely accepted standard notation for biomedical entities. Thus, automatic systems for the identification of citations of allelic variants of genes in biomedical texts are required.ResultsOur group has previously reported the development of OSIRIS, a system aimed at the retrieval of literature about allelic variants of genes http://ibi.imim.es/osirisform.html. Here we describe the development of a new version of OSIRIS (OSIRISv1.2, http://ibi.imim.es/OSIRISv1.2.html) which incorporates a new entity recognition module and is built on top of a local mirror of the MEDLINE collection and HgenetInfoDB: a database that collects data on human gene sequence variations. The new entity recognition module is based on a pattern-based search algorithm for the identification of variation terms in the texts and their mapping to dbSNP identifiers. The performance of OSIRISv1.2 was evaluated on a manually annotated corpus, resulting in 99% precision, 82% recall, and an F-score of 0.89. As an example, the application of the system for collecting literature citations for the allelic variants of genes related to the diseases intracranial aneurysm and breast cancer is presented.ConclusionOSIRISv1.2 can be used to link literature references to dbSNP database entries with high accuracy, and therefore is suitable for collecting current knowledge on gene sequence variations and supporting the functional annotation of variation databases. The application of OSIRISv1.2 in combination with controlled vocabularies like MeSH provides a way to identify associations of biomedical interest, such as those that relate SNPs with diseases.

Dataset Information

Exploiting and assessing multi-source data for supervised biomedical named entity recognition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets