@inproceedings{azmat-etal-2020-constructing,
title = "Constructing {U}yghur Name Entity Recognition System using Neural Machine Translation Tag Projection",
author = "Azmat, Anwar and
Xiao, Li and
Yating, Yang and
Rui, Dong and
Turghun, Osman",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.93",
pages = "1006--1016",
abstract = "Although named entity recognition achieved great success by introducing the neural networks, it is challenging to apply these models to low resource languages including Uyghur while it depends on a large amount of annotated training data. Constructing a well-annotated named entity corpus manually is very time-consuming and labor-intensive. Most existing methods based on the parallel corpus combined with the word alignment tools. However, word alignment methods introduce alignment errors inevitably. In this paper, we address this problem by a named entity tag transfer method based on the common neural machine translation. The proposed method marks the entity boundaries in Chinese sentence and translates the sentences to Uyghur by neural machine translation system, hope that neural machine translation will align the source and target entity by the self-attention mechanism. The experimental results show that the Uyghur named entity recognition system trained by the constructed corpus achieve good performance on the test set, with 73.80{\%} F1 score(3.79{\%} improvement by baseline)",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azmat-etal-2020-constructing">
<titleInfo>
<title>Constructing Uyghur Name Entity Recognition System using Neural Machine Translation Tag Projection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anwar</namePart>
<namePart type="family">Azmat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yating</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Rui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Turghun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although named entity recognition achieved great success by introducing the neural networks, it is challenging to apply these models to low resource languages including Uyghur while it depends on a large amount of annotated training data. Constructing a well-annotated named entity corpus manually is very time-consuming and labor-intensive. Most existing methods based on the parallel corpus combined with the word alignment tools. However, word alignment methods introduce alignment errors inevitably. In this paper, we address this problem by a named entity tag transfer method based on the common neural machine translation. The proposed method marks the entity boundaries in Chinese sentence and translates the sentences to Uyghur by neural machine translation system, hope that neural machine translation will align the source and target entity by the self-attention mechanism. The experimental results show that the Uyghur named entity recognition system trained by the constructed corpus achieve good performance on the test set, with 73.80% F1 score(3.79% improvement by baseline)</abstract>
<identifier type="citekey">azmat-etal-2020-constructing</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.93</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>1006</start>
<end>1016</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Uyghur Name Entity Recognition System using Neural Machine Translation Tag Projection
%A Azmat, Anwar
%A Xiao, Li
%A Yating, Yang
%A Rui, Dong
%A Turghun, Osman
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G English
%F azmat-etal-2020-constructing
%X Although named entity recognition achieved great success by introducing the neural networks, it is challenging to apply these models to low resource languages including Uyghur while it depends on a large amount of annotated training data. Constructing a well-annotated named entity corpus manually is very time-consuming and labor-intensive. Most existing methods based on the parallel corpus combined with the word alignment tools. However, word alignment methods introduce alignment errors inevitably. In this paper, we address this problem by a named entity tag transfer method based on the common neural machine translation. The proposed method marks the entity boundaries in Chinese sentence and translates the sentences to Uyghur by neural machine translation system, hope that neural machine translation will align the source and target entity by the self-attention mechanism. The experimental results show that the Uyghur named entity recognition system trained by the constructed corpus achieve good performance on the test set, with 73.80% F1 score(3.79% improvement by baseline)
%U https://aclanthology.org/2020.ccl-1.93
%P 1006-1016
Markdown (Informal)
[Constructing Uyghur Name Entity Recognition System using Neural Machine Translation Tag Projection](https://aclanthology.org/2020.ccl-1.93) (Azmat et al., CCL 2020)
ACL