@inproceedings{nayak-joshi-2022-l3cube,
title = "{L}3{C}ube-{H}ing{C}orpus and {H}ing{BERT}: A Code Mixed {H}indi-{E}nglish Dataset and {BERT} Language Models",
author = "Nayak, Ravindra and
Joshi, Raviraj",
editor = "Jha, Girish Nath and
L., Sobha and
Bali, Kalika and
Ojha, Atul Kr.",
booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.wildre-1.2",
pages = "7--12",
abstract = "Code-switching occurs when more than one language is mixed in a given sentence or a conversation. This phenomenon is more prominent on social media platforms and its adoption is increasing over time. Therefore code-mixed NLP has been extensively studied in the literature. As pre-trained transformer-based architectures are gaining popularity, we observe that real code-mixing data are scarce to pre-train large language models. We present L3Cube-HingCorpus, the first large-scale real Hindi-English code mixed data in a Roman script. It consists of 52.93M sentences and 1.04B tokens, scraped from Twitter. We further present HingBERT, HingMBERT, HingRoBERTa, and HingGPT. The BERT models have been pre-trained on codemixed HingCorpus using masked language modelling objectives. We show the effectiveness of these BERT models on the subsequent downstream tasks like code-mixed sentiment analysis, POS tagging, NER, and LID from the GLUECoS benchmark. The HingGPT is a GPT2 based generative transformer model capable of generating full tweets. Our models show significant improvements over currently available models pre-trained on multiple languages and synthetic code-mixed datasets. We also release L3Cube-HingLID Corpus, the largest code-mixed Hindi-English language identification(LID) dataset and HingBERT-LID, a production-quality LID model to facilitate capturing of more code-mixed data using the process outlined in this work. The dataset and models are available at \url{https://github.com/l3cube-pune/code-mixed-nlp}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayak-joshi-2022-l3cube">
<titleInfo>
<title>L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ravindra</namePart>
<namePart type="family">Nayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raviraj</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="given">Nath</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-switching occurs when more than one language is mixed in a given sentence or a conversation. This phenomenon is more prominent on social media platforms and its adoption is increasing over time. Therefore code-mixed NLP has been extensively studied in the literature. As pre-trained transformer-based architectures are gaining popularity, we observe that real code-mixing data are scarce to pre-train large language models. We present L3Cube-HingCorpus, the first large-scale real Hindi-English code mixed data in a Roman script. It consists of 52.93M sentences and 1.04B tokens, scraped from Twitter. We further present HingBERT, HingMBERT, HingRoBERTa, and HingGPT. The BERT models have been pre-trained on codemixed HingCorpus using masked language modelling objectives. We show the effectiveness of these BERT models on the subsequent downstream tasks like code-mixed sentiment analysis, POS tagging, NER, and LID from the GLUECoS benchmark. The HingGPT is a GPT2 based generative transformer model capable of generating full tweets. Our models show significant improvements over currently available models pre-trained on multiple languages and synthetic code-mixed datasets. We also release L3Cube-HingLID Corpus, the largest code-mixed Hindi-English language identification(LID) dataset and HingBERT-LID, a production-quality LID model to facilitate capturing of more code-mixed data using the process outlined in this work. The dataset and models are available at https://github.com/l3cube-pune/code-mixed-nlp.</abstract>
<identifier type="citekey">nayak-joshi-2022-l3cube</identifier>
<location>
<url>https://aclanthology.org/2022.wildre-1.2</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models
%A Nayak, Ravindra
%A Joshi, Raviraj
%Y Jha, Girish Nath
%Y L., Sobha
%Y Bali, Kalika
%Y Ojha, Atul Kr.
%S Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F nayak-joshi-2022-l3cube
%X Code-switching occurs when more than one language is mixed in a given sentence or a conversation. This phenomenon is more prominent on social media platforms and its adoption is increasing over time. Therefore code-mixed NLP has been extensively studied in the literature. As pre-trained transformer-based architectures are gaining popularity, we observe that real code-mixing data are scarce to pre-train large language models. We present L3Cube-HingCorpus, the first large-scale real Hindi-English code mixed data in a Roman script. It consists of 52.93M sentences and 1.04B tokens, scraped from Twitter. We further present HingBERT, HingMBERT, HingRoBERTa, and HingGPT. The BERT models have been pre-trained on codemixed HingCorpus using masked language modelling objectives. We show the effectiveness of these BERT models on the subsequent downstream tasks like code-mixed sentiment analysis, POS tagging, NER, and LID from the GLUECoS benchmark. The HingGPT is a GPT2 based generative transformer model capable of generating full tweets. Our models show significant improvements over currently available models pre-trained on multiple languages and synthetic code-mixed datasets. We also release L3Cube-HingLID Corpus, the largest code-mixed Hindi-English language identification(LID) dataset and HingBERT-LID, a production-quality LID model to facilitate capturing of more code-mixed data using the process outlined in this work. The dataset and models are available at https://github.com/l3cube-pune/code-mixed-nlp.
%U https://aclanthology.org/2022.wildre-1.2
%P 7-12
Markdown (Informal)
[L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models](https://aclanthology.org/2022.wildre-1.2) (Nayak & Joshi, WILDRE 2022)
ACL