PubTator: a web-based text mining tool for assisting biocuration

Wei, Chih Hsuan; Kao, Hung Yu; Lu, Zhiyong

doi:10.1093/nar/gkt441

Cited by 485 publications

(421 citation statements)

References 23 publications

Supporting

Mentioning

419

Contrasting

Unclassified

Order By: Relevance

“…BioNER can be used to identify new gene names from text [Smith et al, 2008]. It also serves as a primitive step of many downstream applications, such as relation extraction [Cokol et al, 2005] and knowledge base completion [Dai et al, 2010, Gonzalez et al, 2015, Szklarczyk et al, 2017, Wei et al, 2013, Xie et al, 2013, Szklarczyk et al, 2015.…”

Section: Introductionmentioning

confidence: 99%

Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

Wang

Ren

Zhang

et al. 2018

Preprint

View full text Add to dashboard Cite

Motivation: Biomedical named entity recognition (BioNER) is the most fundamental task in biomedical text mining. State-of-the-art BioNER systems often require handcrafted features specifically designed for each type of biomedical entities. This feature generation process requires intensive labors from biomedical and linguistic experts, and makes it difficult to adapt these systems to new biomedical entity types. Although recent studies explored using neural network models for BioNER to free experts from manual feature generation, these models still require substantial human efforts to annotate massive training data. Results: We propose a multi-task learning framework for BioNER that is based on neural network models to save human efforts. We build a global model by collectively training multiple models that share parameters, each model capturing the characteristics of a different biomedical entity type. In experiments on five BioNER benchmark datasets covering four major biomedical entity types, our model outperforms state-ofthe-art systems and other neural network models by a large margin, even when only limited training data are available. Further analysis shows that the large performance gains come from sharing character-and word-level information between different biomedical entities. The approach creates new opportunities for text-mining approaches to help biomedical scientists better exploit knowledge in biomedical literature. Availability: The source code for our models is available at https://github.com/yuzhimanhua/lm-lstm-crf, and the corpora are available at https://github.com/cambridgeltl/MTL-Bioinformatics-2016.

show abstract

Section: Introductionmentioning

confidence: 99%

Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

Wang

Ren

Zhang

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Tight integration of NLP and biomedical research is a recent trend (Huang and Lu, 2015) with a number of groups moving in this direction (Wei et al, 2013;Cejuela et al, 2014;Miwa et al, 2013, for example). For pathway curation, it is important that the results of event extraction technologies become part of curation applications/workflows.…”

Section: Resultsmentioning

confidence: 99%

Extracting Biological Pathway Models From NLP Event Representations

Spranger¹,

Palaniappan²,

Ghosh³

2015

Proceedings of BioNLP 15

View full text Add to dashboard Cite

show abstract

“…To achieve high precision and recall for named entity recognition (NER), HiPub integrates two complementary NER tools: PubTator (Wei et al, 2013) and BEST entity extractor (BEST EE) (Lee,S. et al, 2016).…”

Section: Biomedical Named Entity Recognition Servermentioning

confidence: 99%

“…• HiPub integrates two complementary named-entity recognition (NER) methods to achieve high precision and recall: PubTator (Wei et al, 2013) and BEST entity extractor (BEST EE) (Lee,S. et al, 2016) • HiPub visualizes texts as interactive biomedical entity networks using information from texts and external resources.…”

Section: Introductionmentioning

confidence: 99%

HiPub: translating PubMed and PMC texts to networks for knowledge discovery

et al. 2016

View full text Add to dashboard Cite

Summary: We introduce HiPub, a seamless Chrome browser plug-in that automatically recognizes, annotates and translates biomedical entities from texts into networks for knowledge discovery. Using a combination of two different named-entity recognition resources, HiPub can recognize genes, proteins, diseases, drugs, mutations and cell lines in texts, and achieve high precision and recall. HiPub extracts biomedical entity-relationships from texts to construct context-specific networks, and integrates existing network data from external databases for knowledge discovery. It allows users to add additional entities from related articles, as well as user-defined entities for discovering new and unexpected entity-relationships. HiPub provides functional enrichment analysis on the biomedical entity network, and link-outs to external resources to assist users in learning new entities and relations. Availability and Implementation: HiPub and detailed user guide are available at http://hipub.korea.

show abstract

PubTator: a web-based text mining tool for assisting biocuration

Cited by 485 publications

References 23 publications

Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

Extracting Biological Pathway Models From NLP Event Representations

HiPub: translating PubMed and PMC texts to networks for knowledge discovery

Contact Info

Product

Resources

About