@inproceedings{misawa-etal-2017-character,
title = "Character-based Bidirectional {LSTM}-{CRF} with words and characters for {J}apanese Named Entity Recognition",
author = "Misawa, Shotaro and
Taniguchi, Motoki and
Miura, Yasuhide and
Ohkuma, Tomoko",
editor = "Faruqui, Manaal and
Schuetze, Hinrich and
Trancoso, Isabel and
Yaghoobzadeh, Yadollah",
booktitle = "Proceedings of the First Workshop on Subword and Character Level Models in {NLP}",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4114",
doi = "10.18653/v1/W17-4114",
pages = "97--102",
abstract = "Recently, neural models have shown superior performance over conventional models in NER tasks. These models use CNN to extract sub-word information along with RNN to predict a tag for each word. However, these models have been tested almost entirely on English texts. It remains unclear whether they perform similarly in other languages. We worked on Japanese NER using neural models and discovered two obstacles of the state-of-the-art model. First, CNN is unsuitable for extracting Japanese sub-word information. Secondly, a model predicting a tag for each word cannot extract an entity when a part of a word composes an entity. The contributions of this work are (1) verifying the effectiveness of the state-of-the-art NER model for Japanese, (2) proposing a neural model for predicting a tag for each character using word and character information. Experimentally obtained results demonstrate that our model outperforms the state-of-the-art neural English NER model in Japanese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="misawa-etal-2017-character">
<titleInfo>
<title>Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shotaro</namePart>
<namePart type="family">Misawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Motoki</namePart>
<namePart type="family">Taniguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhide</namePart>
<namePart type="family">Miura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoko</namePart>
<namePart type="family">Ohkuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Subword and Character Level Models in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manaal</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, neural models have shown superior performance over conventional models in NER tasks. These models use CNN to extract sub-word information along with RNN to predict a tag for each word. However, these models have been tested almost entirely on English texts. It remains unclear whether they perform similarly in other languages. We worked on Japanese NER using neural models and discovered two obstacles of the state-of-the-art model. First, CNN is unsuitable for extracting Japanese sub-word information. Secondly, a model predicting a tag for each word cannot extract an entity when a part of a word composes an entity. The contributions of this work are (1) verifying the effectiveness of the state-of-the-art NER model for Japanese, (2) proposing a neural model for predicting a tag for each character using word and character information. Experimentally obtained results demonstrate that our model outperforms the state-of-the-art neural English NER model in Japanese.</abstract>
<identifier type="citekey">misawa-etal-2017-character</identifier>
<identifier type="doi">10.18653/v1/W17-4114</identifier>
<location>
<url>https://aclanthology.org/W17-4114</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>97</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition
%A Misawa, Shotaro
%A Taniguchi, Motoki
%A Miura, Yasuhide
%A Ohkuma, Tomoko
%Y Faruqui, Manaal
%Y Schuetze, Hinrich
%Y Trancoso, Isabel
%Y Yaghoobzadeh, Yadollah
%S Proceedings of the First Workshop on Subword and Character Level Models in NLP
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F misawa-etal-2017-character
%X Recently, neural models have shown superior performance over conventional models in NER tasks. These models use CNN to extract sub-word information along with RNN to predict a tag for each word. However, these models have been tested almost entirely on English texts. It remains unclear whether they perform similarly in other languages. We worked on Japanese NER using neural models and discovered two obstacles of the state-of-the-art model. First, CNN is unsuitable for extracting Japanese sub-word information. Secondly, a model predicting a tag for each word cannot extract an entity when a part of a word composes an entity. The contributions of this work are (1) verifying the effectiveness of the state-of-the-art NER model for Japanese, (2) proposing a neural model for predicting a tag for each character using word and character information. Experimentally obtained results demonstrate that our model outperforms the state-of-the-art neural English NER model in Japanese.
%R 10.18653/v1/W17-4114
%U https://aclanthology.org/W17-4114
%U https://doi.org/10.18653/v1/W17-4114
%P 97-102
Markdown (Informal)
[Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition](https://aclanthology.org/W17-4114) (Misawa et al., SCLeM 2017)
ACL