@inproceedings{boudreau-etal-2020-evaluating,
title = "Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi{'}kmaq Language Modelling",
author = "Boudreau, Jeremie and
Patra, Akankshya and
Suvarna, Ashima and
Cook, Paul",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.333",
pages = "2736--2745",
abstract = "Mi{'}kmaq is an Indigenous language spoken primarily in Eastern Canada. It is polysynthetic and low-resource. In this paper we consider a range of n-gram and RNN language models for Mi{'}kmaq. We find that an RNN language model, initialized with pre-trained fastText embeddings, performs best, highlighting the importance of sub-word information for Mi{'}kmaq language modelling. We further consider approaches to language modelling that incorporate cross-lingual word embeddings, but do not see improvements with these models. Finally we consider language models that operate over segmentations produced by SentencePiece {---} which include sub-word units as tokens {---} as opposed to word-level models. We see improvements for this approach over word-level language models, again indicating that sub-word modelling is important for Mi{'}kmaq language modelling.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boudreau-etal-2020-evaluating">
<titleInfo>
<title>Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremie</namePart>
<namePart type="family">Boudreau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akankshya</namePart>
<namePart type="family">Patra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashima</namePart>
<namePart type="family">Suvarna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</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 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>Mi’kmaq is an Indigenous language spoken primarily in Eastern Canada. It is polysynthetic and low-resource. In this paper we consider a range of n-gram and RNN language models for Mi’kmaq. We find that an RNN language model, initialized with pre-trained fastText embeddings, performs best, highlighting the importance of sub-word information for Mi’kmaq language modelling. We further consider approaches to language modelling that incorporate cross-lingual word embeddings, but do not see improvements with these models. Finally we consider language models that operate over segmentations produced by SentencePiece — which include sub-word units as tokens — as opposed to word-level models. We see improvements for this approach over word-level language models, again indicating that sub-word modelling is important for Mi’kmaq language modelling.</abstract>
<identifier type="citekey">boudreau-etal-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.333</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2736</start>
<end>2745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling
%A Boudreau, Jeremie
%A Patra, Akankshya
%A Suvarna, Ashima
%A Cook, Paul
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F boudreau-etal-2020-evaluating
%X Mi’kmaq is an Indigenous language spoken primarily in Eastern Canada. It is polysynthetic and low-resource. In this paper we consider a range of n-gram and RNN language models for Mi’kmaq. We find that an RNN language model, initialized with pre-trained fastText embeddings, performs best, highlighting the importance of sub-word information for Mi’kmaq language modelling. We further consider approaches to language modelling that incorporate cross-lingual word embeddings, but do not see improvements with these models. Finally we consider language models that operate over segmentations produced by SentencePiece — which include sub-word units as tokens — as opposed to word-level models. We see improvements for this approach over word-level language models, again indicating that sub-word modelling is important for Mi’kmaq language modelling.
%U https://aclanthology.org/2020.lrec-1.333
%P 2736-2745
Markdown (Informal)
[Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling](https://aclanthology.org/2020.lrec-1.333) (Boudreau et al., LREC 2020)
ACL