@inproceedings{ben-milad-2021-comparison,
title = "A Comparison of the Word Similarity Measurement in {E}nglish-{A}rabic Translation Memory Segment Retrieval Including an Inflectional Affix Intervention",
author = "Ben Milad, Khaled",
editor = "Mitkov, Ruslan and
Sosoni, Vilelmini and
Gigu{\`e}re, Julie Christine and
Murgolo, Elena and
Deysel, Elizabeth",
booktitle = "Proceedings of the Translation and Interpreting Technology Online Conference",
month = jul,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.triton-1.14",
pages = "125--141",
abstract = "The aim of this paper is to investigate the similarity measurement approach of translation memory (TM) in five representative computer-aided translation (CAT) tools when retrieving inflectional verb-variation sentences in Arabic to English translation. In English, inflectional affixes in verbs include suffixes only; unlike English, verbs in Arabic derive voice, mood, tense, number and person through various inflectional affixes e.g. pre or post a verb root. The research question focuses on establishing whether the TM similarity algorithm measures a combination of the inflectional affixes as a word or as a character intervention when retrieving a segment. If it is dealt with as a character intervention, are the types of intervention penalized equally or differently? This paper experimentally examines, through a black box testing methodology and a test suite instrument, the penalties that TM systems{'} current algorithms impose when input segments and retrieved TM sources are exactly the same, except for a difference in an inflectional affix. It would be expected that, if TM systems had some linguistic knowledge, the penalty would be very light, which would be useful to translators, since a high-scoring match would be presented near the top of the list of proposals. However, analysis of TM systems{'} output shows that inflectional affixes are penalized more heavily than expected, and in different ways. They may be treated as an intervention on the whole word, or as a single character change.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ben-milad-2021-comparison">
<titleInfo>
<title>A Comparison of the Word Similarity Measurement in English-Arabic Translation Memory Segment Retrieval Including an Inflectional Affix Intervention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Ben Milad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Translation and Interpreting Technology Online Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vilelmini</namePart>
<namePart type="family">Sosoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="given">Christine</namePart>
<namePart type="family">Giguère</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Deysel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The aim of this paper is to investigate the similarity measurement approach of translation memory (TM) in five representative computer-aided translation (CAT) tools when retrieving inflectional verb-variation sentences in Arabic to English translation. In English, inflectional affixes in verbs include suffixes only; unlike English, verbs in Arabic derive voice, mood, tense, number and person through various inflectional affixes e.g. pre or post a verb root. The research question focuses on establishing whether the TM similarity algorithm measures a combination of the inflectional affixes as a word or as a character intervention when retrieving a segment. If it is dealt with as a character intervention, are the types of intervention penalized equally or differently? This paper experimentally examines, through a black box testing methodology and a test suite instrument, the penalties that TM systems’ current algorithms impose when input segments and retrieved TM sources are exactly the same, except for a difference in an inflectional affix. It would be expected that, if TM systems had some linguistic knowledge, the penalty would be very light, which would be useful to translators, since a high-scoring match would be presented near the top of the list of proposals. However, analysis of TM systems’ output shows that inflectional affixes are penalized more heavily than expected, and in different ways. They may be treated as an intervention on the whole word, or as a single character change.</abstract>
<identifier type="citekey">ben-milad-2021-comparison</identifier>
<location>
<url>https://aclanthology.org/2021.triton-1.14</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>125</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparison of the Word Similarity Measurement in English-Arabic Translation Memory Segment Retrieval Including an Inflectional Affix Intervention
%A Ben Milad, Khaled
%Y Mitkov, Ruslan
%Y Sosoni, Vilelmini
%Y Giguère, Julie Christine
%Y Murgolo, Elena
%Y Deysel, Elizabeth
%S Proceedings of the Translation and Interpreting Technology Online Conference
%D 2021
%8 July
%I INCOMA Ltd.
%C Held Online
%F ben-milad-2021-comparison
%X The aim of this paper is to investigate the similarity measurement approach of translation memory (TM) in five representative computer-aided translation (CAT) tools when retrieving inflectional verb-variation sentences in Arabic to English translation. In English, inflectional affixes in verbs include suffixes only; unlike English, verbs in Arabic derive voice, mood, tense, number and person through various inflectional affixes e.g. pre or post a verb root. The research question focuses on establishing whether the TM similarity algorithm measures a combination of the inflectional affixes as a word or as a character intervention when retrieving a segment. If it is dealt with as a character intervention, are the types of intervention penalized equally or differently? This paper experimentally examines, through a black box testing methodology and a test suite instrument, the penalties that TM systems’ current algorithms impose when input segments and retrieved TM sources are exactly the same, except for a difference in an inflectional affix. It would be expected that, if TM systems had some linguistic knowledge, the penalty would be very light, which would be useful to translators, since a high-scoring match would be presented near the top of the list of proposals. However, analysis of TM systems’ output shows that inflectional affixes are penalized more heavily than expected, and in different ways. They may be treated as an intervention on the whole word, or as a single character change.
%U https://aclanthology.org/2021.triton-1.14
%P 125-141
Markdown (Informal)
[A Comparison of the Word Similarity Measurement in English-Arabic Translation Memory Segment Retrieval Including an Inflectional Affix Intervention](https://aclanthology.org/2021.triton-1.14) (Ben Milad, TRITON 2021)
ACL