Learning A Unified Named Entity Tagger From Multiple Partially Annotated Corpora For Efficient Adaptation
Preprint
Abstract
Named entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream applications and accordingly only cover a small set of entity types relevant to a particular task. For instance, in the biomedical domain, one corpus might annotate genes, another chemicals, and another diseases---despite the texts in each corpus containing references to all three types of entities. In this paper, we propose a deep structured model to integrate these "partially annotated" datasets to jointly identify all entity types appearing in the training corpora. By leveraging multiple datasets, the model can learn robust input representations; by building a joint structured model, it avoids potential conflicts caused by combining several models' predictions at test time. Experiments show that the proposed model significantly outperforms strong multi-task learning baselines when training on multiple, partially annotated datasets and testing on datasets that contain tags from more than one of the training corpora.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Cross-type biomedical named entity recognition with deep multi-task learningBioinformatics, 2018
- Empower Sequence Labeling with Task-Aware Neural Language ModelProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Neural Architectures for Named Entity Recognition2016
- CHEMDNER system with mixed conditional random fields and multi-scale word clusteringJournal of Cheminformatics, 2015
- CHEMDNER: The drugs and chemical names extraction challengeJournal of Cheminformatics, 2015
- NCBI disease corpus: A resource for disease name recognition and concept normalizationJournal of Biomedical Informatics, 2014
- Anatomical entity mention recognition at literature scaleBioinformatics, 2013
- LINNAEUS: A species name identification system for biomedical literatureBMC Bioinformatics, 2010
- Learning from Positive and Unlabeled Examples with Different Data Distributions2005
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994