@inproceedings{chatterjere-etal-2020-minority,
title = "Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling",
author = "Chatterjere, Arindam and
Guptha, Vineeth and
Chopra, Parul and
Das, Amitava",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.764/",
pages = "6228--6236",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Code-Mixing (CM) or language mixing is a social norm in multilingual societies. CM is quite prevalent in social media conversations in multilingual regions like - India, Europe, Canada and Mexico. In this paper, we explore the problem of Language Modeling (LM) for code-mixed Hinglish text. In recent times, there have been several success stories with neural language modeling like Generative Pre-trained Transformer (GPT) (Radford et al., 2019), Bidirectional Encoder Representations from Transformers (BERT) (Devlin et al., 2018) etc.. Hence, neural language models have become the new holy grail of modern NLP, although LM for CM is an unexplored area altogether. To better understand the problem of LM for CM, we initially experimented with several statistical language modeling techniques and consequently experimented with contemporary neural language models. Analysis shows switching-points are the main challenge for the LMCM performance drop, therefore in this paper we introduce the idea of minority positive sampling to selectively induce more sample to achieve better performance. On the contrary, all neural language models demand a huge corpus to train on for better performance. Finally, we are reporting a perplexity of 139 for Hinglish (Hindi-English language pair) LMCM using statistical bi-directional techniques."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatterjere-etal-2020-minority">
<titleInfo>
<title>Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arindam</namePart>
<namePart type="family">Chatterjere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vineeth</namePart>
<namePart type="family">Guptha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parul</namePart>
<namePart type="family">Chopra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amitava</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Code-Mixing (CM) or language mixing is a social norm in multilingual societies. CM is quite prevalent in social media conversations in multilingual regions like - India, Europe, Canada and Mexico. In this paper, we explore the problem of Language Modeling (LM) for code-mixed Hinglish text. In recent times, there have been several success stories with neural language modeling like Generative Pre-trained Transformer (GPT) (Radford et al., 2019), Bidirectional Encoder Representations from Transformers (BERT) (Devlin et al., 2018) etc.. Hence, neural language models have become the new holy grail of modern NLP, although LM for CM is an unexplored area altogether. To better understand the problem of LM for CM, we initially experimented with several statistical language modeling techniques and consequently experimented with contemporary neural language models. Analysis shows switching-points are the main challenge for the LMCM performance drop, therefore in this paper we introduce the idea of minority positive sampling to selectively induce more sample to achieve better performance. On the contrary, all neural language models demand a huge corpus to train on for better performance. Finally, we are reporting a perplexity of 139 for Hinglish (Hindi-English language pair) LMCM using statistical bi-directional techniques.</abstract>
<identifier type="citekey">chatterjere-etal-2020-minority</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.764/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6228</start>
<end>6236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling
%A Chatterjere, Arindam
%A Guptha, Vineeth
%A Chopra, Parul
%A Das, Amitava
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F chatterjere-etal-2020-minority
%X Code-Mixing (CM) or language mixing is a social norm in multilingual societies. CM is quite prevalent in social media conversations in multilingual regions like - India, Europe, Canada and Mexico. In this paper, we explore the problem of Language Modeling (LM) for code-mixed Hinglish text. In recent times, there have been several success stories with neural language modeling like Generative Pre-trained Transformer (GPT) (Radford et al., 2019), Bidirectional Encoder Representations from Transformers (BERT) (Devlin et al., 2018) etc.. Hence, neural language models have become the new holy grail of modern NLP, although LM for CM is an unexplored area altogether. To better understand the problem of LM for CM, we initially experimented with several statistical language modeling techniques and consequently experimented with contemporary neural language models. Analysis shows switching-points are the main challenge for the LMCM performance drop, therefore in this paper we introduce the idea of minority positive sampling to selectively induce more sample to achieve better performance. On the contrary, all neural language models demand a huge corpus to train on for better performance. Finally, we are reporting a perplexity of 139 for Hinglish (Hindi-English language pair) LMCM using statistical bi-directional techniques.
%U https://aclanthology.org/2020.lrec-1.764/
%P 6228-6236
Markdown (Informal)
[Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling](https://aclanthology.org/2020.lrec-1.764/) (Chatterjere et al., LREC 2020)
ACL