Machine Translation (MT) research has witnessed continuous growth, accompanied by an increasing demand for automated error detection and correction in textual content. In response, Unbabel has developed a hybrid approach that combines machine translation with human editors in post-edition (PE) to provide high-quality translations. To facilitate the tasks of post-editors, Unbabel has created a proprietary error ...
This paper proposes a typology concerning errors and linguistic structures found in the source text that have an impact on Machine Translation (MT). The main objectives of this project were firstly, to make a comparison between error typologies and analyze them according to their suitability; analyze annotated data and build a data-driven typology while adapting the previous existing typologies; make a distinct...
Neste trabalho propõe-se um fragmento de português controlado para a Tradução Automática. A linguagem controlada proposta é do tipo Machine-oriented Controlled Language (MOCL), ou seja, orientada para a máquina, em concreto, para a redação de textos a serem traduzidos por um sistema de tradução automática. Em termos de cobertura lexical, este fragmento não se destina a um domínio específico, pelo que, dado o se...