@inproceedings{gasser-etal-2020-character,
title = "Character Alignment in Morphologically Complex Translation Sets for Related Languages",
author = "Gasser, Michael and
Seyoum, Binyam Ephrem and
Kifle, Nazareth Amlesom",
booktitle = "Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics (ICCL)",
url = "https://aclanthology.org/2020.vardial-1.5",
pages = "47--56",
abstract = "For languages with complex morphology, word-to-word translation is a task with various potential applications, for example, in information retrieval, language instruction, and dictionary creation, as well as in machine translation. In this paper, we confine ourselves to the subtask of character alignment for the particular case of families of related languages with very few resources for most or all members. There are many such families; we focus on the subgroup of Semitic languages spoken in Ethiopia and Eritrea. We begin with an adaptation of the familiar alignment algorithms behind statistical machine translation, modifying them as appropriate for our task. We show how character alignment can reveal morphological, phonological, and orthographic correspondences among related languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gasser-etal-2020-character">
<titleInfo>
<title>Character Alignment in Morphologically Complex Translation Sets for Related Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gasser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyam</namePart>
<namePart type="given">Ephrem</namePart>
<namePart type="family">Seyoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazareth</namePart>
<namePart type="given">Amlesom</namePart>
<namePart type="family">Kifle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics (ICCL)</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For languages with complex morphology, word-to-word translation is a task with various potential applications, for example, in information retrieval, language instruction, and dictionary creation, as well as in machine translation. In this paper, we confine ourselves to the subtask of character alignment for the particular case of families of related languages with very few resources for most or all members. There are many such families; we focus on the subgroup of Semitic languages spoken in Ethiopia and Eritrea. We begin with an adaptation of the familiar alignment algorithms behind statistical machine translation, modifying them as appropriate for our task. We show how character alignment can reveal morphological, phonological, and orthographic correspondences among related languages.</abstract>
<identifier type="citekey">gasser-etal-2020-character</identifier>
<location>
<url>https://aclanthology.org/2020.vardial-1.5</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>47</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character Alignment in Morphologically Complex Translation Sets for Related Languages
%A Gasser, Michael
%A Seyoum, Binyam Ephrem
%A Kifle, Nazareth Amlesom
%S Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2020
%8 dec
%I International Committee on Computational Linguistics (ICCL)
%C Barcelona, Spain (Online)
%F gasser-etal-2020-character
%X For languages with complex morphology, word-to-word translation is a task with various potential applications, for example, in information retrieval, language instruction, and dictionary creation, as well as in machine translation. In this paper, we confine ourselves to the subtask of character alignment for the particular case of families of related languages with very few resources for most or all members. There are many such families; we focus on the subgroup of Semitic languages spoken in Ethiopia and Eritrea. We begin with an adaptation of the familiar alignment algorithms behind statistical machine translation, modifying them as appropriate for our task. We show how character alignment can reveal morphological, phonological, and orthographic correspondences among related languages.
%U https://aclanthology.org/2020.vardial-1.5
%P 47-56
Markdown (Informal)
[Character Alignment in Morphologically Complex Translation Sets for Related Languages](https://aclanthology.org/2020.vardial-1.5) (Gasser et al., VarDial 2020)
ACL