SemSyn: Semantic-Syntactic Similarity Based Automatic Machine Translation Evaluation Metric
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A6JBIV92E" target="_blank" >RIV/00216208:11320/23:6JBIV92E - isvavai.cz</a>
Výsledek na webu
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85153234419&doi=10.1080%2f03772063.2023.2195819&partnerID=40&md5=f3bdce827d4a018759de4cfc6f5f1a05" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85153234419&doi=10.1080%2f03772063.2023.2195819&partnerID=40&md5=f3bdce827d4a018759de4cfc6f5f1a05</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1080/03772063.2023.2195819" target="_blank" >10.1080/03772063.2023.2195819</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
SemSyn: Semantic-Syntactic Similarity Based Automatic Machine Translation Evaluation Metric
Popis výsledku v původním jazyce
"Machine translation evaluation is difficult and challenging for natural languages because different languages behave differently for the same dataset. Lexical-based metrics have been poorly represented semantic relationships and impose strict identity matching. However, translation and assessment become difficult for target morphologically rich languages with relatively free word order. Most of the standard evaluation metrics consider word order but do not effectively consider sentence structure. In this paper, we propose a novel machine translation evaluation metric SemSyn which incorporates both semantic and syntactic similarity. We incorporate the term frequency-inverse document frequency with the earth mover’s distance and word embedding to cover the semantic similarity. The part of speech and dependency parsing tags assist in covering syntactic similarity in the sentence structure. Part of speech and dependency parsing tags are extracted from universal dependencies and trained on the SpaCy library. Experimental results show that SemSyn has a higher correlation with human judgment than other evaluation metrics for morphologically rich language and other languages. © 2023 IETE."
Název v anglickém jazyce
SemSyn: Semantic-Syntactic Similarity Based Automatic Machine Translation Evaluation Metric
Popis výsledku anglicky
"Machine translation evaluation is difficult and challenging for natural languages because different languages behave differently for the same dataset. Lexical-based metrics have been poorly represented semantic relationships and impose strict identity matching. However, translation and assessment become difficult for target morphologically rich languages with relatively free word order. Most of the standard evaluation metrics consider word order but do not effectively consider sentence structure. In this paper, we propose a novel machine translation evaluation metric SemSyn which incorporates both semantic and syntactic similarity. We incorporate the term frequency-inverse document frequency with the earth mover’s distance and word embedding to cover the semantic similarity. The part of speech and dependency parsing tags assist in covering syntactic similarity in the sentence structure. Part of speech and dependency parsing tags are extracted from universal dependencies and trained on the SpaCy library. Experimental results show that SemSyn has a higher correlation with human judgment than other evaluation metrics for morphologically rich language and other languages. © 2023 IETE."
Klasifikace
Druh
J<sub>SC</sub> - Článek v periodiku v databázi SCOPUS
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
"IETE Journal of Research"
ISSN
0377-2063
e-ISSN
—
Svazek periodika
""
Číslo periodika v rámci svazku
2023
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
12
Strana od-do
1-12
Kód UT WoS článku
000974191200001
EID výsledku v databázi Scopus
2-s2.0-85153234419