Machine Translation for Languages Lacking Bitext via Multilingual Gloss Transduction
نویسندگان
چکیده
We propose and evaluate a new paradigm for machine translation of low resource languages via the learned surface transduction and paraphrase of multilingual glosses.
منابع مشابه
Multilingual eXtended WordNet Knowledge Base: Semantic Parsing and Translation of Glosses
This paper presents a method to create WordNet-like lexical resources for different languages. Instead of directly translating glosses from one language to another, we perform first semantic parsing of WordNet glosses and then translate the resulting semantic representation. The proposed approach simplifies the machine translation of the glosses. The approach provides ready to use semantic repr...
متن کاملImproving Word Alignment with Bridge Languages
We describe an approach to improve Statistical Machine Translation (SMT) performance using multi-lingual, parallel, sentence-aligned corpora in several bridge languages. Our approach consists of a simple method for utilizing a bridge language to create a word alignment system and a procedure for combining word alignment systems from multiple bridge languages. The final translation is obtained b...
متن کاملSource Language Adaptation Approaches for Resource-Poor Machine Translation
Most of the world languages are resource-poor for statistical machine translation; still, many of them are actually related to some resource-rich language. Thus, we propose three novel, language-independent approaches to source language adaptation for resource-poor statistical machine translation. Specifically, we build improved statistical machine translation models from a resource-poor langua...
متن کاملUsing multilingual content on the web to build fast finite-state direct translation systems
In this paper I try to identify and describe in certain detail a possible avenue of research in machine translation: the use of existing multilingual content on the web and finite-state technology to automatically build and maintain fast web-based direct machine translation systems, especially for language pairs lacking machine translation resources. The term direct is used to refer to systems ...
متن کاملBuilding Language Resources and Translation Models for Machine Translation Focused on South Slavic and Balkan Languages
The aim of this short-term project was to investigate the feasibility of machine translation (MT) research and development for several South Slavic and Balkan languages, more precisely Romanian, Bulgarian, Slovene, Greek and Serbian. For these languages, MT systems are scarce and for some of them even non-existent. We provide a brief description of the project’s major research tasks: Compilatio...
متن کامل