@inproceedings{sung-etal-2021-cnnbif-cnn,
title = "{CNNB}i{F}: {CNN}-based Bigram Features for Named Entity Recognition",
author = "Sung, Chul and
Goel, Vaibhava and
Marcheret, Etienne and
Rennie, Steven and
Nahamoo, David",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.87",
doi = "10.18653/v1/2021.findings-emnlp.87",
pages = "1016--1021",
abstract = "Transformer models fine-tuned with a sequence labeling objective have become the dominant choice for named entity recognition tasks. However, a self-attention mechanism with unconstrained length can fail to fully capture local dependencies, particularly when training data is limited. In this paper, we propose a novel joint training objective which better captures the semantics of words corresponding to the same entity. By augmenting the training objective with a group-consistency loss component we enhance our ability to capture local dependencies while still enjoying the advantages of the unconstrained self-attention mechanism. On the CoNLL2003 dataset, our method achieves a test F1 of 93.98 with a single transformer model. More importantly our fine-tuned CoNLL2003 model displays significant gains in generalization to out of domain datasets: on the OntoNotes subset we achieve an F1 of 72.67 which is 0.49 points absolute better than the baseline, and on the WNUT16 set an F1 of 68.22 which is a gain of 0.48 points. Furthermore, on the WNUT17 dataset we achieve an F1 of 55.85, yielding a 2.92 point absolute improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2021-cnnbif-cnn">
<titleInfo>
<title>CNNBiF: CNN-based Bigram Features for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chul</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaibhava</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Etienne</namePart>
<namePart type="family">Marcheret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Rennie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Nahamoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformer models fine-tuned with a sequence labeling objective have become the dominant choice for named entity recognition tasks. However, a self-attention mechanism with unconstrained length can fail to fully capture local dependencies, particularly when training data is limited. In this paper, we propose a novel joint training objective which better captures the semantics of words corresponding to the same entity. By augmenting the training objective with a group-consistency loss component we enhance our ability to capture local dependencies while still enjoying the advantages of the unconstrained self-attention mechanism. On the CoNLL2003 dataset, our method achieves a test F1 of 93.98 with a single transformer model. More importantly our fine-tuned CoNLL2003 model displays significant gains in generalization to out of domain datasets: on the OntoNotes subset we achieve an F1 of 72.67 which is 0.49 points absolute better than the baseline, and on the WNUT16 set an F1 of 68.22 which is a gain of 0.48 points. Furthermore, on the WNUT17 dataset we achieve an F1 of 55.85, yielding a 2.92 point absolute improvement.</abstract>
<identifier type="citekey">sung-etal-2021-cnnbif-cnn</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.87</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.87</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1016</start>
<end>1021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CNNBiF: CNN-based Bigram Features for Named Entity Recognition
%A Sung, Chul
%A Goel, Vaibhava
%A Marcheret, Etienne
%A Rennie, Steven
%A Nahamoo, David
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F sung-etal-2021-cnnbif-cnn
%X Transformer models fine-tuned with a sequence labeling objective have become the dominant choice for named entity recognition tasks. However, a self-attention mechanism with unconstrained length can fail to fully capture local dependencies, particularly when training data is limited. In this paper, we propose a novel joint training objective which better captures the semantics of words corresponding to the same entity. By augmenting the training objective with a group-consistency loss component we enhance our ability to capture local dependencies while still enjoying the advantages of the unconstrained self-attention mechanism. On the CoNLL2003 dataset, our method achieves a test F1 of 93.98 with a single transformer model. More importantly our fine-tuned CoNLL2003 model displays significant gains in generalization to out of domain datasets: on the OntoNotes subset we achieve an F1 of 72.67 which is 0.49 points absolute better than the baseline, and on the WNUT16 set an F1 of 68.22 which is a gain of 0.48 points. Furthermore, on the WNUT17 dataset we achieve an F1 of 55.85, yielding a 2.92 point absolute improvement.
%R 10.18653/v1/2021.findings-emnlp.87
%U https://aclanthology.org/2021.findings-emnlp.87
%U https://doi.org/10.18653/v1/2021.findings-emnlp.87
%P 1016-1021
Markdown (Informal)
[CNNBiF: CNN-based Bigram Features for Named Entity Recognition](https://aclanthology.org/2021.findings-emnlp.87) (Sung et al., Findings 2021)
ACL
- Chul Sung, Vaibhava Goel, Etienne Marcheret, Steven Rennie, and David Nahamoo. 2021. CNNBiF: CNN-based Bigram Features for Named Entity Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1016–1021, Punta Cana, Dominican Republic. Association for Computational Linguistics.