@inproceedings{joanis-etal-2020-nunavut,
title = "The {N}unavut {H}ansard {I}nuktitut{--}{E}nglish Parallel Corpus 3.0 with Preliminary Machine Translation Results",
author = "Joanis, Eric and
Knowles, Rebecca and
Kuhn, Roland and
Larkin, Samuel and
Littell, Patrick and
Lo, Chi-kiu and
Stewart, Darlene and
Micher, Jeffrey",
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-1.312",
pages = "2562--2572",
abstract = "The Inuktitut language, a member of the Inuit-Yupik-Unangan language family, is spoken across Arctic Canada and noted for its morphological complexity. It is an official language of two territories, Nunavut and the Northwest Territories, and has recognition in additional regions. This paper describes a newly released sentence-aligned Inuktitut{--}English corpus based on the proceedings of the Legislative Assembly of Nunavut, covering sessions from April 1999 to June 2017. With approximately 1.3 million aligned sentence pairs, this is, to our knowledge, the largest parallel corpus of a polysynthetic language or an Indigenous language of the Americas released to date. The paper describes the alignment methodology used, the evaluation of the alignments, and preliminary experiments on statistical and neural machine translation (SMT and NMT) between Inuktitut and English, in both directions.",
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="joanis-etal-2020-nunavut">
<titleInfo>
<title>The Nunavut Hansard Inuktitut–English Parallel Corpus 3.0 with Preliminary Machine Translation Results</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Joanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Knowles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Larkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Littell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi-kiu</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darlene</namePart>
<namePart type="family">Stewart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Micher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</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 Twelfth 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>The Inuktitut language, a member of the Inuit-Yupik-Unangan language family, is spoken across Arctic Canada and noted for its morphological complexity. It is an official language of two territories, Nunavut and the Northwest Territories, and has recognition in additional regions. This paper describes a newly released sentence-aligned Inuktitut–English corpus based on the proceedings of the Legislative Assembly of Nunavut, covering sessions from April 1999 to June 2017. With approximately 1.3 million aligned sentence pairs, this is, to our knowledge, the largest parallel corpus of a polysynthetic language or an Indigenous language of the Americas released to date. The paper describes the alignment methodology used, the evaluation of the alignments, and preliminary experiments on statistical and neural machine translation (SMT and NMT) between Inuktitut and English, in both directions.</abstract>
<identifier type="citekey">joanis-etal-2020-nunavut</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.312</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2562</start>
<end>2572</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Nunavut Hansard Inuktitut–English Parallel Corpus 3.0 with Preliminary Machine Translation Results
%A Joanis, Eric
%A Knowles, Rebecca
%A Kuhn, Roland
%A Larkin, Samuel
%A Littell, Patrick
%A Lo, Chi-kiu
%A Stewart, Darlene
%A Micher, Jeffrey
%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 English
%F joanis-etal-2020-nunavut
%X The Inuktitut language, a member of the Inuit-Yupik-Unangan language family, is spoken across Arctic Canada and noted for its morphological complexity. It is an official language of two territories, Nunavut and the Northwest Territories, and has recognition in additional regions. This paper describes a newly released sentence-aligned Inuktitut–English corpus based on the proceedings of the Legislative Assembly of Nunavut, covering sessions from April 1999 to June 2017. With approximately 1.3 million aligned sentence pairs, this is, to our knowledge, the largest parallel corpus of a polysynthetic language or an Indigenous language of the Americas released to date. The paper describes the alignment methodology used, the evaluation of the alignments, and preliminary experiments on statistical and neural machine translation (SMT and NMT) between Inuktitut and English, in both directions.
%U https://aclanthology.org/2020.lrec-1.312
%P 2562-2572
Markdown (Informal)
[The Nunavut Hansard Inuktitut–English Parallel Corpus 3.0 with Preliminary Machine Translation Results](https://aclanthology.org/2020.lrec-1.312) (Joanis et al., LREC 2020)
ACL
- Eric Joanis, Rebecca Knowles, Roland Kuhn, Samuel Larkin, Patrick Littell, Chi-kiu Lo, Darlene Stewart, and Jeffrey Micher. 2020. The Nunavut Hansard Inuktitut–English Parallel Corpus 3.0 with Preliminary Machine Translation Results. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2562–2572, Marseille, France. European Language Resources Association.