A Machine Translation Model Inspired by Code Generation

In this paper we present our machine translation model that is based on bilingual linguistic phrases and their lexical attributes. Developed model partly arises from our previous work in the field of Generative Programming, and the working prototype was made for Croatian-French and French-Croatian t...

Full description

Saved in:
Bibliographic Details
Main Authors: Radošević, Danijel, Magdalenić, Ivan, Andročec, Darko, Bernik, Andrija, Kaniški, Matija
Format: Conference Proceeding
Language:English
Subjects:
Bilingualism
Cooking
Dictionaries
Domains
English language
International conferences
Linguistics
Machine translation
Methods
Natural language
Search engines
Weather forecasting
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we present our machine translation model that is based on bilingual linguistic phrases and their lexical attributes. Developed model partly arises from our previous work in the field of Generative Programming, and the working prototype was made for Croatian-French and French-Croatian translation. The model is aimed for the general language domain, but it is so far mostly trained for some limited domains like cooking recipes, weather forecast and user manuals for different devices. The proposed model was evaluated according to the matched phrases and by using the BLEU machine translation evaluation method.
ISSN:1847-2001
1848-2295