@inproceedings{williams-2017-boundary,
title = "Boundary-based {MWE} segmentation with text partitioning",
author = "Williams, Jake",
editor = "Derczynski, Leon and
Xu, Wei and
Ritter, Alan and
Baldwin, Tim",
booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4401",
doi = "10.18653/v1/W17-4401",
pages = "1--10",
abstract = "This submission describes the development of a fine-grained, text-chunking algorithm for the task of comprehensive MWE segmentation. This task notably focuses on the identification of colloquial and idiomatic language. The submission also includes a thorough model evaluation in the context of two recent shared tasks, spanning 19 different languages and many text domains, including noisy, user-generated text. Evaluations exhibit the presented model as the best overall for purposes of MWE segmentation, and open-source software is released with the submission (although links are withheld for purposes of anonymity). Additionally, the authors acknowledge the existence of a pre-print document on arxiv.org, which should be avoided to maintain anonymity in review.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="williams-2017-boundary">
<titleInfo>
<title>Boundary-based MWE segmentation with text partitioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Williams</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 3rd Workshop on Noisy User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</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>This submission describes the development of a fine-grained, text-chunking algorithm for the task of comprehensive MWE segmentation. This task notably focuses on the identification of colloquial and idiomatic language. The submission also includes a thorough model evaluation in the context of two recent shared tasks, spanning 19 different languages and many text domains, including noisy, user-generated text. Evaluations exhibit the presented model as the best overall for purposes of MWE segmentation, and open-source software is released with the submission (although links are withheld for purposes of anonymity). Additionally, the authors acknowledge the existence of a pre-print document on arxiv.org, which should be avoided to maintain anonymity in review.</abstract>
<identifier type="citekey">williams-2017-boundary</identifier>
<identifier type="doi">10.18653/v1/W17-4401</identifier>
<location>
<url>https://aclanthology.org/W17-4401</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Boundary-based MWE segmentation with text partitioning
%A Williams, Jake
%Y Derczynski, Leon
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%S Proceedings of the 3rd Workshop on Noisy User-generated Text
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F williams-2017-boundary
%X This submission describes the development of a fine-grained, text-chunking algorithm for the task of comprehensive MWE segmentation. This task notably focuses on the identification of colloquial and idiomatic language. The submission also includes a thorough model evaluation in the context of two recent shared tasks, spanning 19 different languages and many text domains, including noisy, user-generated text. Evaluations exhibit the presented model as the best overall for purposes of MWE segmentation, and open-source software is released with the submission (although links are withheld for purposes of anonymity). Additionally, the authors acknowledge the existence of a pre-print document on arxiv.org, which should be avoided to maintain anonymity in review.
%R 10.18653/v1/W17-4401
%U https://aclanthology.org/W17-4401
%U https://doi.org/10.18653/v1/W17-4401
%P 1-10
Markdown (Informal)
[Boundary-based MWE segmentation with text partitioning](https://aclanthology.org/W17-4401) (Williams, WNUT 2017)
ACL