LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools
Abstract Background Chemical and biomedical named entity recognition (NER) is an essential preprocessing task in natural language processing. The identification and extraction of named entities from scientific articles is also attracting increasing interest in many scientific disciplines. Locating c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-01-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13321-018-0327-2 |
| _version_ | 1819204073725886464 |
|---|---|
| author | Wahed Hemati Alexander Mehler |
| author_facet | Wahed Hemati Alexander Mehler |
| author_sort | Wahed Hemati |
| collection | DOAJ |
| description | Abstract Background Chemical and biomedical named entity recognition (NER) is an essential preprocessing task in natural language processing. The identification and extraction of named entities from scientific articles is also attracting increasing interest in many scientific disciplines. Locating chemical named entities in the literature is an essential step in chemical text mining pipelines for identifying chemical mentions, their properties, and relations as discussed in the literature. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of chemical named entities. For this purpose, we transform the task of NER into a sequence labeling problem. We present a series of sequence labeling systems that we used, adapted and optimized in our experiments for solving this task. To this end, we experiment with hyperparameter optimization. Finally, we present LSTMVoter, a two-stage application of recurrent neural networks that integrates the optimized sequence labelers from our study into a single ensemble classifier. Results We introduce LSTMVoter, a bidirectional long short-term memory (LSTM) tagger that utilizes a conditional random field layer in conjunction with attention-based feature modeling. Our approach explores information about features that is modeled by means of an attention mechanism. LSTMVoter outperforms each extractor integrated by it in a series of experiments. On the BioCreative IV chemical compound and drug name recognition (CHEMDNER) corpus, LSTMVoter achieves an F1-score of 90.04%; on the BioCreative V.5 chemical entity mention in patents corpus, it achieves an F1-score of 89.01%. Availability and implementation Data and code are available at https://github.com/texttechnologylab/LSTMVoter. |
| first_indexed | 2024-12-23T04:30:01Z |
| format | Article |
| id | doaj.art-beb6d613fd7a49578cf84fa7a947153c |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-12-23T04:30:01Z |
| publishDate | 2019-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-beb6d613fd7a49578cf84fa7a947153c2022-12-21T18:00:04ZengBMCJournal of Cheminformatics1758-29462019-01-011111710.1186/s13321-018-0327-2LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling toolsWahed Hemati0Alexander Mehler1Text Technology Lab, Goethe-University FrankfurtText Technology Lab, Goethe-University FrankfurtAbstract Background Chemical and biomedical named entity recognition (NER) is an essential preprocessing task in natural language processing. The identification and extraction of named entities from scientific articles is also attracting increasing interest in many scientific disciplines. Locating chemical named entities in the literature is an essential step in chemical text mining pipelines for identifying chemical mentions, their properties, and relations as discussed in the literature. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of chemical named entities. For this purpose, we transform the task of NER into a sequence labeling problem. We present a series of sequence labeling systems that we used, adapted and optimized in our experiments for solving this task. To this end, we experiment with hyperparameter optimization. Finally, we present LSTMVoter, a two-stage application of recurrent neural networks that integrates the optimized sequence labelers from our study into a single ensemble classifier. Results We introduce LSTMVoter, a bidirectional long short-term memory (LSTM) tagger that utilizes a conditional random field layer in conjunction with attention-based feature modeling. Our approach explores information about features that is modeled by means of an attention mechanism. LSTMVoter outperforms each extractor integrated by it in a series of experiments. On the BioCreative IV chemical compound and drug name recognition (CHEMDNER) corpus, LSTMVoter achieves an F1-score of 90.04%; on the BioCreative V.5 chemical entity mention in patents corpus, it achieves an F1-score of 89.01%. Availability and implementation Data and code are available at https://github.com/texttechnologylab/LSTMVoter.http://link.springer.com/article/10.1186/s13321-018-0327-2BioCreative V.5CEMPCHEMDNERBioNLPNamed entity recognitionDeep learning |
| spellingShingle | Wahed Hemati Alexander Mehler LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools Journal of Cheminformatics BioCreative V.5 CEMP CHEMDNER BioNLP Named entity recognition Deep learning |
| title | LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools |
| title_full | LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools |
| title_fullStr | LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools |
| title_full_unstemmed | LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools |
| title_short | LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools |
| title_sort | lstmvoter chemical named entity recognition using a conglomerate of sequence labeling tools |
| topic | BioCreative V.5 CEMP CHEMDNER BioNLP Named entity recognition Deep learning |
| url | http://link.springer.com/article/10.1186/s13321-018-0327-2 |
| work_keys_str_mv | AT wahedhemati lstmvoterchemicalnamedentityrecognitionusingaconglomerateofsequencelabelingtools AT alexandermehler lstmvoterchemicalnamedentityrecognitionusingaconglomerateofsequencelabelingtools |