The Important Influencing Factors in Machine Translation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AV774VZWA" target="_blank" >RIV/00216208:11320/23:V774VZWA - isvavai.cz</a>
Result on the web
<a href="https://www.springerprofessional.de/en/the-important-influencing-factors-in-machine-translation/25456456" target="_blank" >https://www.springerprofessional.de/en/the-important-influencing-factors-in-machine-translation/25456456</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-15175-0_10" target="_blank" >10.1007/978-3-031-15175-0_10</a>
Alternative languages
Result language
angličtina
Original language name
The Important Influencing Factors in Machine Translation
Original language description
"Factored-based machine translation deals with various important linguistics information of a word during the translation process. Morphologically rich languages like Hindi provide multiple word forms from the root or dictionary word by differing in morphological information such as part of speech (POS), affixes, number, gender, etc. So, linguistic factors can provide useful information while translating morphologically rich languages. Different factors contribute in a different manner. In this chapter, we study the significance of different linguistic factors in a phrase-based statistical machine translation (SMT) framework employed for Hindi to English translation. We performed experiments over HindEnCorp and ILCI dataset for Hindi–English. We find that POS+lemma+gender achieves the highest BLEU score (16.46) for HindEnCorp dataset, and POS+lemma+number achieves the highest BLEU score (19.11) for ILCI dataset."
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
"Machine Learning and Big Data Analytics"
ISBN
978-3-031-15175-0
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
119-126
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Cham
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—