@inproceedings{matsushita-etal-2021-improving,
title = "Improving Neural Language Processing with Named Entities",
author = "Matsushita, Kyoumoto and
Makino, Takuya and
Iwakura, Tomoya",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.107",
pages = "940--949",
abstract = "Pretraining-based neural network models have demonstrated state-of-the-art (SOTA) performances on natural language processing (NLP) tasks. The most frequently used sentence representation for neural-based NLP methods is a sequence of subwords that is different from the sentence representation of non-neural methods that are created using basic NLP technologies, such as part-of-speech (POS) tagging, named entity (NE) recognition, and parsing. Most neural-based NLP models receive only vectors encoded from a sequence of subwords obtained from an input text. However, basic NLP information, such as POS tags, NEs, parsing results, etc, cannot be obtained explicitly from only the large unlabeled text used in pretraining-based models. This paper explores use of NEs on two Japanese tasks; document classification and headline generation using Transformer-based models, to reveal the effectiveness of basic NLP information. The experimental results with eight basic NEs and approximately 200 extended NEs show that NEs improve accuracy although a large pretraining-based model trained using 70 GB text data was used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matsushita-etal-2021-improving">
<titleInfo>
<title>Improving Neural Language Processing with Named Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyoumoto</namePart>
<namePart type="family">Matsushita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takuya</namePart>
<namePart type="family">Makino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Iwakura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretraining-based neural network models have demonstrated state-of-the-art (SOTA) performances on natural language processing (NLP) tasks. The most frequently used sentence representation for neural-based NLP methods is a sequence of subwords that is different from the sentence representation of non-neural methods that are created using basic NLP technologies, such as part-of-speech (POS) tagging, named entity (NE) recognition, and parsing. Most neural-based NLP models receive only vectors encoded from a sequence of subwords obtained from an input text. However, basic NLP information, such as POS tags, NEs, parsing results, etc, cannot be obtained explicitly from only the large unlabeled text used in pretraining-based models. This paper explores use of NEs on two Japanese tasks; document classification and headline generation using Transformer-based models, to reveal the effectiveness of basic NLP information. The experimental results with eight basic NEs and approximately 200 extended NEs show that NEs improve accuracy although a large pretraining-based model trained using 70 GB text data was used.</abstract>
<identifier type="citekey">matsushita-etal-2021-improving</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.107</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>940</start>
<end>949</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Neural Language Processing with Named Entities
%A Matsushita, Kyoumoto
%A Makino, Takuya
%A Iwakura, Tomoya
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F matsushita-etal-2021-improving
%X Pretraining-based neural network models have demonstrated state-of-the-art (SOTA) performances on natural language processing (NLP) tasks. The most frequently used sentence representation for neural-based NLP methods is a sequence of subwords that is different from the sentence representation of non-neural methods that are created using basic NLP technologies, such as part-of-speech (POS) tagging, named entity (NE) recognition, and parsing. Most neural-based NLP models receive only vectors encoded from a sequence of subwords obtained from an input text. However, basic NLP information, such as POS tags, NEs, parsing results, etc, cannot be obtained explicitly from only the large unlabeled text used in pretraining-based models. This paper explores use of NEs on two Japanese tasks; document classification and headline generation using Transformer-based models, to reveal the effectiveness of basic NLP information. The experimental results with eight basic NEs and approximately 200 extended NEs show that NEs improve accuracy although a large pretraining-based model trained using 70 GB text data was used.
%U https://aclanthology.org/2021.ranlp-1.107
%P 940-949
Markdown (Informal)
[Improving Neural Language Processing with Named Entities](https://aclanthology.org/2021.ranlp-1.107) (Matsushita et al., RANLP 2021)
ACL