To date, the non-manual components of signed utterances have rarely been considered in automatic sign language translation. However, these components are capable of carrying important linguistic information. This paper presents work that bridges the gap between the output of a sign language translation system and the input of a sign language animation system by incorporating non-manual informat...

This paper describes UNITRAN, an implemented machine translation system that translates Spanish, English, and German bidirectionally. The primary characteristic of UNITRAN is that it operates cross-linguistically (i.e., uniformly across all languages), while still accounting for knowledge that is specific to each language. The task of cross-linguistic translation is difficult because there are ...

the most important and practical phase of analyzing the linguistic errors of second language learners is to find the solutions to decrease these errors. to that end, the present study examined translation strategy to decrease the number of grammatical and lexical errors of chinese language learners learning persian. twelve chinese language learners were asked to write a text in two stages. firs...

A current increasing trend in machine translation is to combine data-driven and rule-based techniques. Such combinations typically involve the hybridization of different paradigms such as, for instance, the introduction of linguistic knowledge into statistical paradigms, the incorporation of data-driven components into rulebased paradigms, or the preand postprocessing of either sort of translat...

While object-oriented programming languages are good at modelling real-world concepts and benefit from rich libraries and developer tools, logic programming languages are well suited for declaratively solving computational problems that require knowledge reasoning. Nontrivial declarative applications could take advantage of the modelling features of object-oriented programming and of the rich s...

Alternative assessment approaches received considerable attention soon after a discontent with traditional, one-shot testing. These approaches, however, have been used only to improve learners’ linguistic ability despite communicative models of language which pointed that knowledge of language also involves pragmatic ability (Bachman, 1990; Bachman & Palmer, 1996). The present study tries to ex...

Motivation of the language technology company Tilde is to improve quality of machine translation for lesser resourced languages such as the languages of Baltic countries. Generic MT solutions like Google Translate perform poorly for these complex languages. To compensate the shortage of training data and to deal with rich morphology we are applying different approaches in combining statistical ...

Globalisation is bringing translation and multilingual information processing to areas where it was previously unknown, relatively unimportant, or technically just not feasible. Today, Natural Language Understanding techniques are important for reaching global audiences, and are therefore becoming an indispensable component inside many systems and workflows. The main subjects of discussion cont...