BANNER: An Executable Survey of Advances in Biomedical Named Entity Recognition

By Robert Leaman, Graciela Gonzalez. Pacific Symposium on Biocomputing, 2007

578 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/2d871bb34be5e5d824e6e2af313f47ae025f93ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Bridging semantics and syntax with graph algorithms —state-of-the-art of extracting biomedical relations (2015, background): “They noted that in general a significant performance drop will occur when using named entities tagged by NER system such as BANNER [141] instead of using the gold standard.”
Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features (2015, methodology): “15,41,42 We used CRFsuite, the implementation provided by Okazaki, 43 as it is fast and provides a simple interface for training/modifying the input features.”
tmVar: a text mining approach for extracting sequence variants in biomedical literature (2013, methodology): “Following VTag and other previous studies on biomedical named entities (Doğan and Lu, 2012b; Hsu et al., 2008; Leaman and Gonzalez, 2008), we formulated the problem of named entity recognition as a sequence-labeling problem.”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, background): “They noted that in general a significant performance drop will occur when using named entities tagged by NER system such as BANNER [190] instead of using the gold standard.”
Enhancing clinical concept extraction with distributional semantics (2011, methodology): “2, features from a state of the art biomedical NER system, BANNER [56], were adapted to create the baseline.”
DNorm: disease name normalization with pairwise learning to rank (2013, methodology): “Disease mentions are then located using the BANNER named entity recognizer (Leaman and Gonzalez, 2008).”
Deep learning meets ontologies: experiments to anchor the cardiovascular disease ontology in the biomedical literature (2018, background): “Machine Learning (ML) approaches such as conditional random fields [5] that is used in ABNER [6] and BANNER [7].”
Unsupervised entity and relation extraction from clinical records in Italian (2016, unknown): “BANNER is another machine-learning system, also based on CRFs, described in [19], which also contains a wide survey of the features adopted for named entity recognition in biomedical texts.”
tmChem: a high performance approach for chemical named entity recognition and normalization (2015, methodology): “Model 1 is an adaptation of the BANNER named entity recognizer to chemicals [22].”
Chemical-induced disease relation extraction via convolutional neural network (2017, methodology): “Following the previous work (18), a simple tokenizer (32) was used for tokenization and the Stanford CoreNLP Tool (33) was employed for sentence splitting, part-of-speech tagging and lemmatization.”
Deep learning with word embeddings improves biomedical named entity recognition (2017, methodology): “tmChem Model I trains a first-order CRF using features from BANNER (Leaman and Gonzalez, 2008) plus further ones obtained through a trial-and-error procedure, including character n-grams, chemical specific identifiers, and the output of ChemSpot (Rockt€aschel et al.”
The CHEMDNER corpus of chemicals and drugs and its annotation principles (2015, background): “Text mining and information extraction techniques are showing promising results in the biomedical domain: A range of applications have been implemented [2] to detect bio-entities [3,4] and their relations (e.”
TaggerOne: joint named entity recognition and normalization with semi-Markov Models (2016, methodology): “Token-level feature templates are similar to previous work in biomedical NER (Leaman and Gonzalez, 2008; Leaman, et al., 2015), including: • Token text, token stem • Part of speech • Character 2, 3 and 4 - grams • Patterns to recognize numbers and common variations in cap- italization Feature…”
Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task (2016, methodology): “DNorm combines an approach based on rich features and conditional random fields for named entity recognition [using BANNER (25)] with a novel machine learning method for normalization based on pairwise learning to rank (26).”
A Survey on Recent Advances in Named Entity Recognition from Deep Learning models (2018, background): “There have also been surveys focused on NER systems for speciﬁc domains and languages, including biomedical NER, (Leaman and Gonzalez, 2008), Chinese clinical NER (Lei et al., 2013), Arabic NER (Shaalan, 2014; Etaiwi et al., 2017), and NER for Indian languages (Patil et al., 2016).”
NCBI disease corpus: A resource for disease name recognition and concept normalization (2014, methodology): “To evaluate its performance in an ab initio setting, first BANNER [40] was applied on each PubMed abstract for disease mention recognition, and then, the Inference Method was applied for disease name normalization.”