@inproceedings{greenberg-etal-2018-marginal,
title = "Marginal Likelihood Training of {B}i{LSTM}-{CRF} for Biomedical Named Entity Recognition from Disjoint Label Sets",
author = "Greenberg, Nathan and
Bansal, Trapit and
Verga, Patrick and
McCallum, Andrew",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1306",
doi = "10.18653/v1/D18-1306",
pages = "2824--2829",
abstract = "Extracting typed entity mentions from text is a fundamental component to language understanding and reasoning. While there exist substantial labeled text datasets for multiple subsets of biomedical entity types{---}such as genes and proteins, or chemicals and diseases{---}it is rare to find large labeled datasets containing labels for all desired entity types together. This paper presents a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types. Our approach employs marginal likelihood training to insist on labels that are present in the data, while filling in {``}missing labels{''}. This allows us to leverage all the available data within a single model. In experimental results on the Biocreative V CDR (chemicals/diseases), Biocreative VI ChemProt (chemicals/proteins) and MedMentions (19 entity types) datasets, we show that joint training on multiple datasets improves NER F1 over training in isolation, and our methods achieve state-of-the-art results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="greenberg-etal-2018-marginal">
<titleInfo>
<title>Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Greenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Verga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extracting typed entity mentions from text is a fundamental component to language understanding and reasoning. While there exist substantial labeled text datasets for multiple subsets of biomedical entity types—such as genes and proteins, or chemicals and diseases—it is rare to find large labeled datasets containing labels for all desired entity types together. This paper presents a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types. Our approach employs marginal likelihood training to insist on labels that are present in the data, while filling in “missing labels”. This allows us to leverage all the available data within a single model. In experimental results on the Biocreative V CDR (chemicals/diseases), Biocreative VI ChemProt (chemicals/proteins) and MedMentions (19 entity types) datasets, we show that joint training on multiple datasets improves NER F1 over training in isolation, and our methods achieve state-of-the-art results.</abstract>
<identifier type="citekey">greenberg-etal-2018-marginal</identifier>
<identifier type="doi">10.18653/v1/D18-1306</identifier>
<location>
<url>https://aclanthology.org/D18-1306</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2824</start>
<end>2829</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets
%A Greenberg, Nathan
%A Bansal, Trapit
%A Verga, Patrick
%A McCallum, Andrew
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F greenberg-etal-2018-marginal
%X Extracting typed entity mentions from text is a fundamental component to language understanding and reasoning. While there exist substantial labeled text datasets for multiple subsets of biomedical entity types—such as genes and proteins, or chemicals and diseases—it is rare to find large labeled datasets containing labels for all desired entity types together. This paper presents a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types. Our approach employs marginal likelihood training to insist on labels that are present in the data, while filling in “missing labels”. This allows us to leverage all the available data within a single model. In experimental results on the Biocreative V CDR (chemicals/diseases), Biocreative VI ChemProt (chemicals/proteins) and MedMentions (19 entity types) datasets, we show that joint training on multiple datasets improves NER F1 over training in isolation, and our methods achieve state-of-the-art results.
%R 10.18653/v1/D18-1306
%U https://aclanthology.org/D18-1306
%U https://doi.org/10.18653/v1/D18-1306
%P 2824-2829
Markdown (Informal)
[Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets](https://aclanthology.org/D18-1306) (Greenberg et al., EMNLP 2018)
ACL