@inproceedings{baruah-etal-2024-assamesebacktranslit,
title = "{A}ssamese{B}ack{T}ranslit: Back Transliteration of {R}omanized {A}ssamese Social Media Text",
author = "Baruah, Hemanta and
Singh, Sanasam Ranbir and
Sarmah, Priyankoo",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.143",
pages = "1627--1637",
abstract = "This paper presents a novel back transliteration dataset capturing native language text originally composed in the Roman/Latin script, harvested from popular social media platforms, along with its corresponding representation in the native Assamese script. Assamese, categorized as a low-resource language within the Indo-Aryan language family, predominantly spoken in the north-east Indian state of Assam, faces a scarcity of linguistic resources. The dataset comprises a total of 60,312 Roman-native parallel transliterated sentences. This paper diverges from conventional forward transliteration datasets consisting mainly of named entities and technical terms, instead presenting a novel transliteration dataset cultivated from three prominent social media platforms, Facebook, Twitter(currently X), and YouTube, in the backward transliteration direction. The paper offers a comprehensive examination of ten state-of-the-art word-level transliteration models within the context of this dataset, encompassing transliteration evaluation benchmarks, extensive performance assessments, and a discussion of the unique chal- lenges encountered during the processing of transliterated social media content. Our approach involves the initial use of two statistical transliteration models, followed by the training of two state-of-the-art neural network-based transliteration models, evaluation of three publicly available pre-trained models, and ultimately fine-tuning one existing state-of-the-art multilingual transliteration model along with two pre-trained large language models using the collected datasets. Notably, the Neural Transformer model outperforms all other baseline transliteration models, achieving the lowest Word Error Rate (WER) and Character Error Rate (CER), and the highest BLEU (up to 4 gram) score of 55.05, 19.44, and 69.15, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baruah-etal-2024-assamesebacktranslit">
<titleInfo>
<title>AssameseBackTranslit: Back Transliteration of Romanized Assamese Social Media Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hemanta</namePart>
<namePart type="family">Baruah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanasam</namePart>
<namePart type="given">Ranbir</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyankoo</namePart>
<namePart type="family">Sarmah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a novel back transliteration dataset capturing native language text originally composed in the Roman/Latin script, harvested from popular social media platforms, along with its corresponding representation in the native Assamese script. Assamese, categorized as a low-resource language within the Indo-Aryan language family, predominantly spoken in the north-east Indian state of Assam, faces a scarcity of linguistic resources. The dataset comprises a total of 60,312 Roman-native parallel transliterated sentences. This paper diverges from conventional forward transliteration datasets consisting mainly of named entities and technical terms, instead presenting a novel transliteration dataset cultivated from three prominent social media platforms, Facebook, Twitter(currently X), and YouTube, in the backward transliteration direction. The paper offers a comprehensive examination of ten state-of-the-art word-level transliteration models within the context of this dataset, encompassing transliteration evaluation benchmarks, extensive performance assessments, and a discussion of the unique chal- lenges encountered during the processing of transliterated social media content. Our approach involves the initial use of two statistical transliteration models, followed by the training of two state-of-the-art neural network-based transliteration models, evaluation of three publicly available pre-trained models, and ultimately fine-tuning one existing state-of-the-art multilingual transliteration model along with two pre-trained large language models using the collected datasets. Notably, the Neural Transformer model outperforms all other baseline transliteration models, achieving the lowest Word Error Rate (WER) and Character Error Rate (CER), and the highest BLEU (up to 4 gram) score of 55.05, 19.44, and 69.15, respectively.</abstract>
<identifier type="citekey">baruah-etal-2024-assamesebacktranslit</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.143</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1627</start>
<end>1637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AssameseBackTranslit: Back Transliteration of Romanized Assamese Social Media Text
%A Baruah, Hemanta
%A Singh, Sanasam Ranbir
%A Sarmah, Priyankoo
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F baruah-etal-2024-assamesebacktranslit
%X This paper presents a novel back transliteration dataset capturing native language text originally composed in the Roman/Latin script, harvested from popular social media platforms, along with its corresponding representation in the native Assamese script. Assamese, categorized as a low-resource language within the Indo-Aryan language family, predominantly spoken in the north-east Indian state of Assam, faces a scarcity of linguistic resources. The dataset comprises a total of 60,312 Roman-native parallel transliterated sentences. This paper diverges from conventional forward transliteration datasets consisting mainly of named entities and technical terms, instead presenting a novel transliteration dataset cultivated from three prominent social media platforms, Facebook, Twitter(currently X), and YouTube, in the backward transliteration direction. The paper offers a comprehensive examination of ten state-of-the-art word-level transliteration models within the context of this dataset, encompassing transliteration evaluation benchmarks, extensive performance assessments, and a discussion of the unique chal- lenges encountered during the processing of transliterated social media content. Our approach involves the initial use of two statistical transliteration models, followed by the training of two state-of-the-art neural network-based transliteration models, evaluation of three publicly available pre-trained models, and ultimately fine-tuning one existing state-of-the-art multilingual transliteration model along with two pre-trained large language models using the collected datasets. Notably, the Neural Transformer model outperforms all other baseline transliteration models, achieving the lowest Word Error Rate (WER) and Character Error Rate (CER), and the highest BLEU (up to 4 gram) score of 55.05, 19.44, and 69.15, respectively.
%U https://aclanthology.org/2024.lrec-main.143
%P 1627-1637
Markdown (Informal)
[AssameseBackTranslit: Back Transliteration of Romanized Assamese Social Media Text](https://aclanthology.org/2024.lrec-main.143) (Baruah et al., LREC-COLING 2024)
ACL