TaggerOne: joint named entity recognition and normalization with semi-Markov Models

By Robert Leaman, Zhiyong Lu. 2016

293 citations recorded by the source corpus.

MOTIVATION Text mining is increasingly used to manage the accelerating pace of the biomedical literature. Many text mining applications depend on accurate named entity recognition (NER) and normalization (grounding). While high performing machine learning methods trainable for many entity types exist for NER, normalization methods are usually specialized to a single entity type. NER and normalization systems are also typically used in a serial pipeline, causing cascading errors and limiting the ability of the NER system to directly exploit the lexical information provided by the normalization. METHODS We propose the first machine learning model for joint NER and normalization during both training and prediction. The model is trainable for arbitrary entity types and consists of a semi-Markov structured linear classifier, with a rich feature approach for NER and supervised semantic indexing for normalization. We also introduce TaggerOne, a Java implementation of our model as a general toolkit for joint NER and normalization. TaggerOne is not specific to any entity type, requiring only annotated training data and a corresponding lexicon, and has been optimized for high throughput. RESULTS We validated TaggerOne with multiple gold-standard corpora containing both mention- and concept-level annotations. Benchmarking results show that TaggerOne achieves high performance on diseases (NCBI Disease corpus, NER f-score: 0.829, normalization f-score: 0.807) and chemicals (BioCreative 5 CDR corpus, NER f-score: 0.914, normalization f-score 0.895). These results compare favorably to the previous state of the art, notwithstanding the greater flexibility of the model. We conclude that jointly modeling NER and normalization greatly improves performance. AVAILABILITY AND IMPLEMENTATION The TaggerOne source code and an online demonstration are available at: http://www.ncbi.nlm.nih.gov/bionlp/taggerone CONTACT zhiyong.lu@nih.gov SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

Subfields: Artificial Intelligence, Molecular Biology

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

Deep learning with word embeddings improves biomedical named entity recognition (2017, methodology): “…(Leaman et al., 2015) Model I, considered as the state-of-the-art chemical NER tool also in other recent studies (Habibi et al., 2016; Leaman and Lu, 2016;). tmChem Model I trains a first-order CRF using features from BANNER (Leaman and Gonzalez, 2008) plus further ones obtained…”
Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets (2018, methodology): “In BioNLP, many highest performing systems still use engineered features fed into a CRF (Wei et al., 2015; Leaman et al., 2015; Leaman and Lu, 2016).”
AI in Health: State of the Art, Challenges, and Future Directions (2019, background): “Recently researchers have also shown that doing joint named entity recognition and normalization together can further boost the performance of both tasks [101, 102]; (ii) relation classification, which is the problem of identifying the relationships among named entities once they have been located i”
Self-Alignment Pretraining for Biomedical Entity Representations (2020, background): “According to (Mohan and Li, 2018), training TaggerOne (Leaman and Lu, 2016), a very popular MEL system, on a subset of Med-Mentions require >900 GB of RAM.”
Deep learning for extracting protein-protein interactions from biomedical literature (2017, background): “…of biomedical information available in the textual form, there has been considerable interest in applying natural language processing (NLP) techniques and machine learning (ML) methods to the biomedical literature (Huang and Lu, 2015; Leaman and Lu, 2016; Singhal et al., 2016; Peng et al., 2016).”