@inproceedings{plank-etal-2020-dan,
title = "{D}a{N}+: {D}anish Nested Named Entities and Lexical Normalization",
author = "Plank, Barbara and
Jensen, Kristian N{\o}rgaard and
van der Goot, Rob",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.583",
doi = "10.18653/v1/2020.coling-main.583",
pages = "6649--6662",
abstract = "This paper introduces DAN+, a new multi-domain corpus and annotation guidelines for Dan-ish nested named entities (NEs) and lexical normalization to support research on cross-lingualcross-domain learning for a less-resourced language. We empirically assess three strategies tomodel the two-layer Named Entity Recognition (NER) task. We compare transfer capabilitiesfrom German versus in-language annotation from scratch. We examine language-specific versusmultilingual BERT, and study the effect of lexical normalization on NER. Our results show that 1) the most robust strategy is multi-task learning which is rivaled by multi-label decoding, 2) BERT-based NER models are sensitive to domain shifts, and 3) in-language BERT and lexicalnormalization are the most beneficial on the least canonical data. Our results also show that anout-of-domain setup remains challenging, while performance on news plateaus quickly. Thishighlights the importance of cross-domain evaluation of cross-lingual transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plank-etal-2020-dan">
<titleInfo>
<title>DaN+: Danish Nested Named Entities and Lexical Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristian</namePart>
<namePart type="given">Nørgaard</namePart>
<namePart type="family">Jensen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces DAN+, a new multi-domain corpus and annotation guidelines for Dan-ish nested named entities (NEs) and lexical normalization to support research on cross-lingualcross-domain learning for a less-resourced language. We empirically assess three strategies tomodel the two-layer Named Entity Recognition (NER) task. We compare transfer capabilitiesfrom German versus in-language annotation from scratch. We examine language-specific versusmultilingual BERT, and study the effect of lexical normalization on NER. Our results show that 1) the most robust strategy is multi-task learning which is rivaled by multi-label decoding, 2) BERT-based NER models are sensitive to domain shifts, and 3) in-language BERT and lexicalnormalization are the most beneficial on the least canonical data. Our results also show that anout-of-domain setup remains challenging, while performance on news plateaus quickly. Thishighlights the importance of cross-domain evaluation of cross-lingual transfer.</abstract>
<identifier type="citekey">plank-etal-2020-dan</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.583</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.583</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6649</start>
<end>6662</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaN+: Danish Nested Named Entities and Lexical Normalization
%A Plank, Barbara
%A Jensen, Kristian Nørgaard
%A van der Goot, Rob
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F plank-etal-2020-dan
%X This paper introduces DAN+, a new multi-domain corpus and annotation guidelines for Dan-ish nested named entities (NEs) and lexical normalization to support research on cross-lingualcross-domain learning for a less-resourced language. We empirically assess three strategies tomodel the two-layer Named Entity Recognition (NER) task. We compare transfer capabilitiesfrom German versus in-language annotation from scratch. We examine language-specific versusmultilingual BERT, and study the effect of lexical normalization on NER. Our results show that 1) the most robust strategy is multi-task learning which is rivaled by multi-label decoding, 2) BERT-based NER models are sensitive to domain shifts, and 3) in-language BERT and lexicalnormalization are the most beneficial on the least canonical data. Our results also show that anout-of-domain setup remains challenging, while performance on news plateaus quickly. Thishighlights the importance of cross-domain evaluation of cross-lingual transfer.
%R 10.18653/v1/2020.coling-main.583
%U https://aclanthology.org/2020.coling-main.583
%U https://doi.org/10.18653/v1/2020.coling-main.583
%P 6649-6662
Markdown (Informal)
[DaN+: Danish Nested Named Entities and Lexical Normalization](https://aclanthology.org/2020.coling-main.583) (Plank et al., COLING 2020)
ACL
- Barbara Plank, Kristian Nørgaard Jensen, and Rob van der Goot. 2020. DaN+: Danish Nested Named Entities and Lexical Normalization. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6649–6662, Barcelona, Spain (Online). International Committee on Computational Linguistics.