Entity recognition in the biomedical domain using a hybrid approach

Basaldella, Marco; Furrer, Lenz; Tasso, Carlo; Rinaldi, Fabio

doi:10.1186/s13326-017-0157-6

Cited by 39 publications

(44 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept annotations of version 3.0 of the corpus are now available in Knowtator 1, Knowtator 2, brat, and UIMA XMI formats (though no longer in AO RDF or Genia XML formats). Version 1.0 was used for evaluations in previous publications (e.g., [4], [5], and [6]), so performance of the sequence-to-sequence method was also evaluated using that first release. The sequence-to-sequence approach was evaluated on version 3.0 as well.…”

Section: Methodsmentioning

confidence: 99%

“…Groza et al [9] approached the task as in information retrieval using case sensitivity and information gain. Basaldella et al [6] described a system relying on high-recall dictionary lookups followed by a highprecision machine learning classifier. We compare our results to each of these systems.…”

Section: Related Workmentioning

confidence: 99%

“…The current state of the art in concept recognition in biomedical texts has been achieved through dictionary lookup [4] or with hybrids of dictionary lookup and machine learning [5,6]. The advantage of dictionary-based systems is that a training dataset is not required.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Biomedical Concept Recognition Using Deep Neural Sequence Models

Bada

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: the automated identification of mentions of ontological concepts in natural language texts is a central task in biomedical information extraction. Despite more than a decade of effort, performance in this task remains below the level necessary for many applications.Results: recently, applications of deep learning in natural language processing have demonstrated striking improvements over previously state-of-the-art performance in many related natural language processing tasks. Here we demonstrate similarly striking performance improvements in recognizing biomedical ontology concepts in full text journal articles using deep learning techniques originally developed for machine translation. For example, our best performing system improves the performance of the previous state-of-the-art in recognizing terms in the Gene Ontology Biological Process hierarchy, from a previous best F1 score of 0.40 to an F1 of 0.70, nearly halving the error rate. Nearly all other ontologies show similar performance improvements. Conclusions:A two-stage concept recognition system, which is a conditional random field model for span detection followed by a deep neural sequence model for normalization, improves the state-of-the-art performance for biomedical concept recognition. Treating the biomedical concept normalization task as a sequence-tosequence mapping task similar to neural machine translation improves performance.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Biomedical Concept Recognition Using Deep Neural Sequence Models

Bada

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Several text mining methods and tools have been developed to solve the problem of named entity recognition by using different approaches [14]. However, to handle with identifying biological entities issues, there are four possible and common approaches [2].…”

Section: Problem Statementmentioning

confidence: 99%

Evaluating Named-Entity Recognition approaches in plant molecular biology

Than²,

Larmande

2018

Preprint

View full text Add to dashboard Cite

Abstract. Text mining research is becoming an important topic in biology with the aim to extract biological entities from scientific papers in order to extend the biological knowledge. However, few thorough studies on text mining and applications are developed for plant molecular biology data, especially rice, thus resulting a lack of datasets available to train models able to detect entities such as genes, proteins and phenotypic traits. Since there is rare benchmarks for rice, we have to face various difficulties in exploiting advanced machine learning methods for accurate analysis of rice bibliography. In this article, we developed a new training datasets (Oryzabase) as the benchmark. Then, we evaluated the performance of several current approaches to find a methodology with the best results and assigned it as the state of the art method for our own technique in the future. We applied Name Entities Recognition (NER) tagger, which is built from a Long Short Term Memory (LSTM) model, and combined with Conditional Random Fields (CRFs) to extract information of rice genes and proteins. We analyzed the performance of LSTM-CRF when applying to the Oryzabase dataset and improved the results up to 86% in F1. We found that on average, the result from LSTM-CRF is more exploitable with the new benchmark.

show abstract

“…NER is followed by a normalization step mapping the entities to a fixed set of identifiers, such as HGNC gene symbols [Yates et al, 2017] or Disease Ontology terms [Kibbe et al, 2015]. General approaches such as LINNAEUS [Gerner et al, 2010], Tagger [Pafilis et al, 2013], taggerOne [Leaman and Lu, 2016], or OGER [Basaldella et al, 2017] recognize diverse biomedical entities in text, while specialized tools recognize mentions of genetic variants [Allot et al, 2018] or chemicals [Jessop et al, 2011].…”

Section: Introductionmentioning

confidence: 99%

CoCoScore: Context-aware co-occurrence scoring for text mining applications using distant supervision

Junge

Jensen

2018

Preprint

View full text Add to dashboard Cite

Information extraction by mining the scientific literature is key to uncovering relations between biomedical entities. Most existing approaches based on natural language processing extract relations from single sentence-level co-mentions, ignoring co-occurrence statistics over the whole corpus. Existing approaches counting entity co-occurrences ignore the textual context of each co-occurrence. We propose a novel corpus-wide co-occurrence scoring approach to relation extraction that takes the textual context of each co-mention into account. Our method, called CoCoScore, scores the certainty of stating an association for each sentence that co-mentions two entities. CoCoScore is trained using distant supervision based on a gold-standard set of associations between entities of interest. Instead of requiring a manually annotated training corpus, co-mentions are labeled as positives/negatives according to their presence/absence in the gold standard. We show that CoCoScore outperforms previous approaches in identifying human disease-gene and tissue-gene associations as well as in identifying physical and functional protein-protein associations in different species. CoCoScore is a versatile text-mining tool to uncover pairwise associations via co-occurrence mining, within and beyond biomedical applications. CoCoScore is available at: https://github.com/JungeAlexander/cocoscore

show abstract

Entity recognition in the biomedical domain using a hybrid approach

Cited by 39 publications

References 39 publications

Biomedical Concept Recognition Using Deep Neural Sequence Models

Biomedical Concept Recognition Using Deep Neural Sequence Models

Evaluating Named-Entity Recognition approaches in plant molecular biology

CoCoScore: Context-aware co-occurrence scoring for text mining applications using distant supervision

Contact Info

Product

Resources

About