Hybrid Filipino-English machine translation system

Approaches in machine translation in the past have been generally classified as either knowledge-based or corpus-based. It has been evident from the inception of machine translation to the present day, that utilizing a single approach, albeit knowledge-based or corpus-based, is not enough to fulfill...

Full description

Saved in:
Bibliographic Details
Main Authors: Fontanilla, Gian Kristian A., Roxas, Rachel Edita O.
Format: text
Published: Animo Repository 2008
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/faculty_research/5122
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
id oai:animorepository.dlsu.edu.ph:faculty_research-6103
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:faculty_research-61032022-07-13T06:19:18Z Hybrid Filipino-English machine translation system Fontanilla, Gian Kristian A. Roxas, Rachel Edita O. Approaches in machine translation in the past have been generally classified as either knowledge-based or corpus-based. It has been evident from the inception of machine translation to the present day, that utilizing a single approach, albeit knowledge-based or corpus-based, is not enough to fulfill the needs of a modern-day machine translation system. In order to address these issues, an amalgamation of approaches is explored to exploit the advantages of both approaches. The hybrid system learns both transfer rules and translation templates from a given training set. Unification constraints are also learned alongside transfer rules, which preserve subject-verb agreement and other linguistic phenomena during translation, which was previously unhandled by its rule-based predecessor. 2008-01-01T08:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/5122 Faculty Research Work Animo Repository Filipino language—Machine translating English language—Machine translating Machine translating Computer Sciences
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
topic Filipino language—Machine translating
English language—Machine translating
Machine translating
Computer Sciences
spellingShingle Filipino language—Machine translating
English language—Machine translating
Machine translating
Computer Sciences
Fontanilla, Gian Kristian A.
Roxas, Rachel Edita O.
Hybrid Filipino-English machine translation system
description Approaches in machine translation in the past have been generally classified as either knowledge-based or corpus-based. It has been evident from the inception of machine translation to the present day, that utilizing a single approach, albeit knowledge-based or corpus-based, is not enough to fulfill the needs of a modern-day machine translation system. In order to address these issues, an amalgamation of approaches is explored to exploit the advantages of both approaches. The hybrid system learns both transfer rules and translation templates from a given training set. Unification constraints are also learned alongside transfer rules, which preserve subject-verb agreement and other linguistic phenomena during translation, which was previously unhandled by its rule-based predecessor.
format text
author Fontanilla, Gian Kristian A.
Roxas, Rachel Edita O.
author_facet Fontanilla, Gian Kristian A.
Roxas, Rachel Edita O.
author_sort Fontanilla, Gian Kristian A.
title Hybrid Filipino-English machine translation system
title_short Hybrid Filipino-English machine translation system
title_full Hybrid Filipino-English machine translation system
title_fullStr Hybrid Filipino-English machine translation system
title_full_unstemmed Hybrid Filipino-English machine translation system
title_sort hybrid filipino-english machine translation system
publisher Animo Repository
publishDate 2008
url https://animorepository.dlsu.edu.ph/faculty_research/5122
_version_ 1767196281506103296