@inproceedings{moran-lignos-2020-effective,
title = "Effective Architectures for Low Resource Multilingual Named Entity Transliteration",
author = "Moran, Molly and
Lignos, Constantine",
editor = "Karakanta, Alina and
Ojha, Atul Kr. and
Liu, Chao-Hong and
Abbott, Jade and
Ortega, John and
Washington, Jonathan and
Oco, Nathaniel and
Lakew, Surafel Melaku and
Pirinen, Tommi A and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.loresmt-1.11",
doi = "10.18653/v1/2020.loresmt-1.11",
pages = "79--86",
abstract = "In this paper, we evaluate LSTM, biLSTM, GRU, and Transformer architectures for the task of name transliteration in a many-to-one multilingual paradigm, transliterating from 590 languages to English. We experiment with different encoder-decoder combinations and evaluate them using accuracy, character error rate, and an F-measure based on longest continuous subsequences. We find that using a Transformer for the encoder and decoder performs best, improving accuracy by over 4 points compared to previous work. We explore whether manipulating the source text by adding macrolanguage flag tokens or pre-romanizing source strings can improve performance and find that neither manipulation has a positive effect. Finally, we analyze performance differences between the LSTM and Transformer encoders when using a Transformer decoder and find that the Transformer encoder is better able to handle insertions and substitutions when transliterating.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moran-lignos-2020-effective">
<titleInfo>
<title>Effective Architectures for Low Resource Multilingual Named Entity Transliteration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Moran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</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 3rd Workshop on Technologies for MT of Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surafel</namePart>
<namePart type="given">Melaku</namePart>
<namePart type="family">Lakew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we evaluate LSTM, biLSTM, GRU, and Transformer architectures for the task of name transliteration in a many-to-one multilingual paradigm, transliterating from 590 languages to English. We experiment with different encoder-decoder combinations and evaluate them using accuracy, character error rate, and an F-measure based on longest continuous subsequences. We find that using a Transformer for the encoder and decoder performs best, improving accuracy by over 4 points compared to previous work. We explore whether manipulating the source text by adding macrolanguage flag tokens or pre-romanizing source strings can improve performance and find that neither manipulation has a positive effect. Finally, we analyze performance differences between the LSTM and Transformer encoders when using a Transformer decoder and find that the Transformer encoder is better able to handle insertions and substitutions when transliterating.</abstract>
<identifier type="citekey">moran-lignos-2020-effective</identifier>
<identifier type="doi">10.18653/v1/2020.loresmt-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.loresmt-1.11</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>79</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Architectures for Low Resource Multilingual Named Entity Transliteration
%A Moran, Molly
%A Lignos, Constantine
%Y Karakanta, Alina
%Y Ojha, Atul Kr.
%Y Liu, Chao-Hong
%Y Abbott, Jade
%Y Ortega, John
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Lakew, Surafel Melaku
%Y Pirinen, Tommi A.
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F moran-lignos-2020-effective
%X In this paper, we evaluate LSTM, biLSTM, GRU, and Transformer architectures for the task of name transliteration in a many-to-one multilingual paradigm, transliterating from 590 languages to English. We experiment with different encoder-decoder combinations and evaluate them using accuracy, character error rate, and an F-measure based on longest continuous subsequences. We find that using a Transformer for the encoder and decoder performs best, improving accuracy by over 4 points compared to previous work. We explore whether manipulating the source text by adding macrolanguage flag tokens or pre-romanizing source strings can improve performance and find that neither manipulation has a positive effect. Finally, we analyze performance differences between the LSTM and Transformer encoders when using a Transformer decoder and find that the Transformer encoder is better able to handle insertions and substitutions when transliterating.
%R 10.18653/v1/2020.loresmt-1.11
%U https://aclanthology.org/2020.loresmt-1.11
%U https://doi.org/10.18653/v1/2020.loresmt-1.11
%P 79-86
Markdown (Informal)
[Effective Architectures for Low Resource Multilingual Named Entity Transliteration](https://aclanthology.org/2020.loresmt-1.11) (Moran & Lignos, LoResMT 2020)
ACL