@inproceedings{pinter-etal-2020-nytwit,
title = "{NYTWIT}: A Dataset of Novel Words in the {N}ew {Y}ork {T}imes",
author = "Pinter, Yuval and
Jacobs, Cassandra L. and
Bittker, Max",
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.572",
doi = "10.18653/v1/2020.coling-main.572",
pages = "6509--6515",
abstract = "We present the New York Times Word Innovation Types dataset, or NYTWIT, a collection of over 2,500 novel English words published in the New York Times between November 2017 and March 2019, manually annotated for their class of novelty (such as lexical derivation, dialectal variation, blending, or compounding). We present baseline results for both uncontextual and contextual prediction of novelty class, showing that there is room for improvement even for state-of-the-art NLP systems. We hope this resource will prove useful for linguists and NLP practitioners by providing a real-world environment of novel word appearance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pinter-etal-2020-nytwit">
<titleInfo>
<title>NYTWIT: A Dataset of Novel Words in the New York Times</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Bittker</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>We present the New York Times Word Innovation Types dataset, or NYTWIT, a collection of over 2,500 novel English words published in the New York Times between November 2017 and March 2019, manually annotated for their class of novelty (such as lexical derivation, dialectal variation, blending, or compounding). We present baseline results for both uncontextual and contextual prediction of novelty class, showing that there is room for improvement even for state-of-the-art NLP systems. We hope this resource will prove useful for linguists and NLP practitioners by providing a real-world environment of novel word appearance.</abstract>
<identifier type="citekey">pinter-etal-2020-nytwit</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.572</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.572</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6509</start>
<end>6515</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NYTWIT: A Dataset of Novel Words in the New York Times
%A Pinter, Yuval
%A Jacobs, Cassandra L.
%A Bittker, Max
%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 pinter-etal-2020-nytwit
%X We present the New York Times Word Innovation Types dataset, or NYTWIT, a collection of over 2,500 novel English words published in the New York Times between November 2017 and March 2019, manually annotated for their class of novelty (such as lexical derivation, dialectal variation, blending, or compounding). We present baseline results for both uncontextual and contextual prediction of novelty class, showing that there is room for improvement even for state-of-the-art NLP systems. We hope this resource will prove useful for linguists and NLP practitioners by providing a real-world environment of novel word appearance.
%R 10.18653/v1/2020.coling-main.572
%U https://aclanthology.org/2020.coling-main.572
%U https://doi.org/10.18653/v1/2020.coling-main.572
%P 6509-6515
Markdown (Informal)
[NYTWIT: A Dataset of Novel Words in the New York Times](https://aclanthology.org/2020.coling-main.572) (Pinter et al., COLING 2020)
ACL
- Yuval Pinter, Cassandra L. Jacobs, and Max Bittker. 2020. NYTWIT: A Dataset of Novel Words in the New York Times. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6509–6515, Barcelona, Spain (Online). International Committee on Computational Linguistics.