@inproceedings{bollmann-etal-2021-moses,
title = "{M}oses and the Character-Based Random Babbling Baseline: {C}o{AS}ta{L} at {A}mericas{NLP} 2021 Shared Task",
author = "Bollmann, Marcel and
Aralikatte, Rahul and
Murrieta Bello, H{\'e}ctor and
Hershcovich, Daniel and
de Lhoneux, Miryam and
S{\o}gaard, Anders",
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.28",
doi = "10.18653/v1/2021.americasnlp-1.28",
pages = "248--254",
abstract = "We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios. Unsuccessfully. In the end, we submitted two runs: (i) a standard phrase-based model, and (ii) a random babbling baseline using character trigrams. We found that it was surprisingly hard to beat (i), in spite of this model being, in theory, a bad fit for polysynthetic languages; and more interestingly, that (ii) was better than several of the submitted systems, highlighting how difficult low-resource machine translation for polysynthetic languages is.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bollmann-etal-2021-moses">
<titleInfo>
<title>Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Bollmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Aralikatte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Héctor</namePart>
<namePart type="family">Murrieta Bello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miryam</namePart>
<namePart type="family">de Lhoneux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios. Unsuccessfully. In the end, we submitted two runs: (i) a standard phrase-based model, and (ii) a random babbling baseline using character trigrams. We found that it was surprisingly hard to beat (i), in spite of this model being, in theory, a bad fit for polysynthetic languages; and more interestingly, that (ii) was better than several of the submitted systems, highlighting how difficult low-resource machine translation for polysynthetic languages is.</abstract>
<identifier type="citekey">bollmann-etal-2021-moses</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.28</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.28</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>248</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task
%A Bollmann, Marcel
%A Aralikatte, Rahul
%A Murrieta Bello, Héctor
%A Hershcovich, Daniel
%A de Lhoneux, Miryam
%A Søgaard, Anders
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F bollmann-etal-2021-moses
%X We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios. Unsuccessfully. In the end, we submitted two runs: (i) a standard phrase-based model, and (ii) a random babbling baseline using character trigrams. We found that it was surprisingly hard to beat (i), in spite of this model being, in theory, a bad fit for polysynthetic languages; and more interestingly, that (ii) was better than several of the submitted systems, highlighting how difficult low-resource machine translation for polysynthetic languages is.
%R 10.18653/v1/2021.americasnlp-1.28
%U https://aclanthology.org/2021.americasnlp-1.28
%U https://doi.org/10.18653/v1/2021.americasnlp-1.28
%P 248-254
Markdown (Informal)
[Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task](https://aclanthology.org/2021.americasnlp-1.28) (Bollmann et al., AmericasNLP 2021)
ACL