@inproceedings{takai-etal-2021-named,
title = "Named Entity-Factored Transformer for Proper Noun Translation",
author = "Takai, Kohichi and
Hattori, Gen and
Yoneyama, Akio and
Yasuda, Keiji and
Sudoh, Katsuhito and
Nakamura, Satoshi",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.2",
pages = "7--11",
abstract = "Subword-based neural machine translation decreases the number of out-of-vocabulary (OOV) words and also keeps the translation quality if input sentences include OOV words. The subword-based NMT decomposes a word into shorter units to solve the OOV problem, but it does not work well for non-compositional proper nouns due to the construction of the shorter unit from words. Furthermore, the lack of translation also occurs in proper noun translation. The proposed method applies the Named Entity (NE) fea-ture vector to Factored Transformer for accurate proper noun translation. The proposed method uses two features which are input sentences in subwords unit and the feature obtained from Named Entity Recognition (NER). The pro-posed method improves the problem of non-compositional proper nouns translation included a low-frequency word. According to the experiments, the proposed method using the best NE feature vector outperformed the baseline sub-word-based transformer model by more than 9.6 points in proper noun accuracy and 2.5 points in the BLEU score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takai-etal-2021-named">
<titleInfo>
<title>Named Entity-Factored Transformer for Proper Noun Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kohichi</namePart>
<namePart type="family">Takai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gen</namePart>
<namePart type="family">Hattori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akio</namePart>
<namePart type="family">Yoneyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keiji</namePart>
<namePart type="family">Yasuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Subword-based neural machine translation decreases the number of out-of-vocabulary (OOV) words and also keeps the translation quality if input sentences include OOV words. The subword-based NMT decomposes a word into shorter units to solve the OOV problem, but it does not work well for non-compositional proper nouns due to the construction of the shorter unit from words. Furthermore, the lack of translation also occurs in proper noun translation. The proposed method applies the Named Entity (NE) fea-ture vector to Factored Transformer for accurate proper noun translation. The proposed method uses two features which are input sentences in subwords unit and the feature obtained from Named Entity Recognition (NER). The pro-posed method improves the problem of non-compositional proper nouns translation included a low-frequency word. According to the experiments, the proposed method using the best NE feature vector outperformed the baseline sub-word-based transformer model by more than 9.6 points in proper noun accuracy and 2.5 points in the BLEU score.</abstract>
<identifier type="citekey">takai-etal-2021-named</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.2</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>7</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity-Factored Transformer for Proper Noun Translation
%A Takai, Kohichi
%A Hattori, Gen
%A Yoneyama, Akio
%A Yasuda, Keiji
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F takai-etal-2021-named
%X Subword-based neural machine translation decreases the number of out-of-vocabulary (OOV) words and also keeps the translation quality if input sentences include OOV words. The subword-based NMT decomposes a word into shorter units to solve the OOV problem, but it does not work well for non-compositional proper nouns due to the construction of the shorter unit from words. Furthermore, the lack of translation also occurs in proper noun translation. The proposed method applies the Named Entity (NE) fea-ture vector to Factored Transformer for accurate proper noun translation. The proposed method uses two features which are input sentences in subwords unit and the feature obtained from Named Entity Recognition (NER). The pro-posed method improves the problem of non-compositional proper nouns translation included a low-frequency word. According to the experiments, the proposed method using the best NE feature vector outperformed the baseline sub-word-based transformer model by more than 9.6 points in proper noun accuracy and 2.5 points in the BLEU score.
%U https://aclanthology.org/2021.icon-main.2
%P 7-11
Markdown (Informal)
[Named Entity-Factored Transformer for Proper Noun Translation](https://aclanthology.org/2021.icon-main.2) (Takai et al., ICON 2021)
ACL
- Kohichi Takai, Gen Hattori, Akio Yoneyama, Keiji Yasuda, Katsuhito Sudoh, and Satoshi Nakamura. 2021. Named Entity-Factored Transformer for Proper Noun Translation. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 7–11, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).