@inproceedings{zhai-etal-2018-comparing,
title = "Comparing {CNN} and {LSTM} character-level embeddings in {B}i{LSTM}-{CRF} models for chemical and disease named entity recognition",
author = "Zhai, Zenan and
Nguyen, Dat Quoc and
Verspoor, Karin",
editor = "Lavelli, Alberto and
Minard, Anne-Lyse and
Rinaldi, Fabio",
booktitle = "Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5605",
doi = "10.18653/v1/W18-5605",
pages = "38--43",
abstract = "We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25{\%} while the LSTM-based character-level word embeddings more than double the required training time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhai-etal-2018-comparing">
<titleInfo>
<title>Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zenan</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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>We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25% while the LSTM-based character-level word embeddings more than double the required training time.</abstract>
<identifier type="citekey">zhai-etal-2018-comparing</identifier>
<identifier type="doi">10.18653/v1/W18-5605</identifier>
<location>
<url>https://aclanthology.org/W18-5605</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>38</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition
%A Zhai, Zenan
%A Nguyen, Dat Quoc
%A Verspoor, Karin
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Rinaldi, Fabio
%S Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F zhai-etal-2018-comparing
%X We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25% while the LSTM-based character-level word embeddings more than double the required training time.
%R 10.18653/v1/W18-5605
%U https://aclanthology.org/W18-5605
%U https://doi.org/10.18653/v1/W18-5605
%P 38-43
Markdown (Informal)
[Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition](https://aclanthology.org/W18-5605) (Zhai et al., Louhi 2018)
ACL