@inproceedings{pivovarova-yangarber-2018-comparison,
title = "Comparison of Representations of Named Entities for Document Classification",
author = "Pivovarova, Lidia and
Yangarber, Roman",
editor = "Augenstein, Isabelle and
Cao, Kris and
He, He and
Hill, Felix and
Gella, Spandana and
Kiros, Jamie and
Mei, Hongyuan and
Misra, Dipendra",
booktitle = "Proceedings of the Third Workshop on Representation Learning for {NLP}",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3008",
doi = "10.18653/v1/W18-3008",
pages = "64--68",
abstract = "We explore representations for multi-word names in text classification tasks, on Reuters (RCV1) topic and sector classification. We find that: the best way to treat names is to split them into tokens and use each token as a separate feature; NEs have more impact on sector classification than topic classification; replacing NEs with entity types is not an effective strategy; representing tokens by different embeddings for proper names vs. common nouns does not improve results. We highlight the improvements over state-of-the-art results that our CNN models yield.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pivovarova-yangarber-2018-comparison">
<titleInfo>
<title>Comparison of Representations of Named Entities for Document Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</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 Third Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamie</namePart>
<namePart type="family">Kiros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyuan</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipendra</namePart>
<namePart type="family">Misra</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 explore representations for multi-word names in text classification tasks, on Reuters (RCV1) topic and sector classification. We find that: the best way to treat names is to split them into tokens and use each token as a separate feature; NEs have more impact on sector classification than topic classification; replacing NEs with entity types is not an effective strategy; representing tokens by different embeddings for proper names vs. common nouns does not improve results. We highlight the improvements over state-of-the-art results that our CNN models yield.</abstract>
<identifier type="citekey">pivovarova-yangarber-2018-comparison</identifier>
<identifier type="doi">10.18653/v1/W18-3008</identifier>
<location>
<url>https://aclanthology.org/W18-3008</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>64</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparison of Representations of Named Entities for Document Classification
%A Pivovarova, Lidia
%A Yangarber, Roman
%Y Augenstein, Isabelle
%Y Cao, Kris
%Y He, He
%Y Hill, Felix
%Y Gella, Spandana
%Y Kiros, Jamie
%Y Mei, Hongyuan
%Y Misra, Dipendra
%S Proceedings of the Third Workshop on Representation Learning for NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F pivovarova-yangarber-2018-comparison
%X We explore representations for multi-word names in text classification tasks, on Reuters (RCV1) topic and sector classification. We find that: the best way to treat names is to split them into tokens and use each token as a separate feature; NEs have more impact on sector classification than topic classification; replacing NEs with entity types is not an effective strategy; representing tokens by different embeddings for proper names vs. common nouns does not improve results. We highlight the improvements over state-of-the-art results that our CNN models yield.
%R 10.18653/v1/W18-3008
%U https://aclanthology.org/W18-3008
%U https://doi.org/10.18653/v1/W18-3008
%P 64-68
Markdown (Informal)
[Comparison of Representations of Named Entities for Document Classification](https://aclanthology.org/W18-3008) (Pivovarova & Yangarber, RepL4NLP 2018)
ACL