@inproceedings{rei-etal-2016-attending,
title = "Attending to Characters in Neural Sequence Labeling Models",
author = "Rei, Marek and
Crichton, Gamal and
Pyysalo, Sampo",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1030",
pages = "309--318",
abstract = "Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rei-etal-2016-attending">
<titleInfo>
<title>Attending to Characters in Neural Sequence Labeling Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gamal</namePart>
<namePart type="family">Crichton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sampo</namePart>
<namePart type="family">Pyysalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.</abstract>
<identifier type="citekey">rei-etal-2016-attending</identifier>
<location>
<url>https://aclanthology.org/C16-1030</url>
</location>
<part>
<date>2016-dec</date>
<extent unit="page">
<start>309</start>
<end>318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attending to Characters in Neural Sequence Labeling Models
%A Rei, Marek
%A Crichton, Gamal
%A Pyysalo, Sampo
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 dec
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F rei-etal-2016-attending
%X Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.
%U https://aclanthology.org/C16-1030
%P 309-318
Markdown (Informal)
[Attending to Characters in Neural Sequence Labeling Models](https://aclanthology.org/C16-1030) (Rei et al., COLING 2016)
ACL
- Marek Rei, Gamal Crichton, and Sampo Pyysalo. 2016. Attending to Characters in Neural Sequence Labeling Models. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 309–318, Osaka, Japan. The COLING 2016 Organizing Committee.