@inproceedings{riedl-pado-2018-named,
title = "A Named Entity Recognition Shootout for {G}erman",
author = "Riedl, Martin and
Pad{\'o}, Sebastian",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2020",
doi = "10.18653/v1/P18-2020",
pages = "120--125",
abstract = "We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the-art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riedl-pado-2018-named">
<titleInfo>
<title>A Named Entity Recognition Shootout for German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Riedl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the-art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.</abstract>
<identifier type="citekey">riedl-pado-2018-named</identifier>
<identifier type="doi">10.18653/v1/P18-2020</identifier>
<location>
<url>https://aclanthology.org/P18-2020</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>120</start>
<end>125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Named Entity Recognition Shootout for German
%A Riedl, Martin
%A Padó, Sebastian
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F riedl-pado-2018-named
%X We ask how to practically build a model for German named entity recognition (NER) that performs at the state of the art for both contemporary and historical texts, i.e., a big-data and a small-data scenario. The two best-performing model families are pitted against each other (linear-chain CRFs and BiLSTM) to observe the trade-off between expressiveness and data requirements. BiLSTM outperforms the CRF when large datasets are available and performs inferior for the smallest dataset. BiLSTMs profit substantially from transfer learning, which enables them to be trained on multiple corpora, resulting in a new state-of-the-art model for German NER on two contemporary German corpora (CoNLL 2003 and GermEval 2014) and two historic corpora.
%R 10.18653/v1/P18-2020
%U https://aclanthology.org/P18-2020
%U https://doi.org/10.18653/v1/P18-2020
%P 120-125
Markdown (Informal)
[A Named Entity Recognition Shootout for German](https://aclanthology.org/P18-2020) (Riedl & Padó, ACL 2018)
ACL
- Martin Riedl and Sebastian Padó. 2018. A Named Entity Recognition Shootout for German. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 120–125, Melbourne, Australia. Association for Computational Linguistics.