In today's multicultural world of multilingual communication and exponential growth of information, specialised texts and terminology, the need for correct understanding and reliable translation is greater than ever. Most Natural Language Processing (NLP) translation tools have been developed by NLP researchers and the practical needs of translators have been virtually ignored. Translators (and interpreters) face the everyday challenge of translating emerging terms which do not appear in dictionaries, and the fact that a very high proportion of these new terms are multiword units, which need to be recognised and translated as such, can only complicate the situation. Unfortunately, translator-orientated practical tools to assist in such scenarios are a scarce commodity, if one at all. This project, which will build on the input from and collaboration with translators, aims to fill in this gap. Its objective is the development of original methodology for, and the implementation of, a novel LAnguage TEchnology platform for tranSlaTors (LATEST). LATEST will go beyond words in that it will automatically identify multiword terms (collocations), and assist translators and interpreters to understand and translate them. It will explain the meaning in specific context by simply clicking on words or expressions. It will also provide the best translation in context by selecting the most appropriate translation from a set of possible translations in the target language.
The innovative methodology underlying the functionalities of the tools to be developed will be based on advanced NLP approaches. A valuable by-product of the project will be the development of new resources (comparable corpora) as well as the development of a tool for automatic compilation of such corpora, which are essential for the operation of LATEST and for the work (translation, documentary search) of translators and interpreters in general.
Field of science
- /natural sciences/computer and information sciences/data science/natural language processing
- /humanities/languages and literature/languages - general
Call for proposal
See other projects for this call