@inproceedings{sanchez-cartagena-etal-2020-understanding,
title = "Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation",
author = "S{\'a}nchez-Cartagena, V{\'\i}ctor M. and
P{\'e}rez-Ortiz, Juan Antonio and
S{\'a}nchez-Mart{\'\i}nez, Felipe",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.349",
doi = "10.18653/v1/2020.coling-main.349",
pages = "3938--3950",
abstract = "This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-cartagena-etal-2020-understanding">
<titleInfo>
<title>Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Pérez-Ortiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Sánchez-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.</abstract>
<identifier type="citekey">sanchez-cartagena-etal-2020-understanding</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.349</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.349</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3938</start>
<end>3950</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation
%A Sánchez-Cartagena, Víctor M.
%A Pérez-Ortiz, Juan Antonio
%A Sánchez-Martínez, Felipe
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F sanchez-cartagena-etal-2020-understanding
%X This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.
%R 10.18653/v1/2020.coling-main.349
%U https://aclanthology.org/2020.coling-main.349
%U https://doi.org/10.18653/v1/2020.coling-main.349
%P 3938-3950
Markdown (Informal)
[Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation](https://aclanthology.org/2020.coling-main.349) (Sánchez-Cartagena et al., COLING 2020)
ACL