Word Sense Disambiguation in Tongue2Tongue, a Pioneering Computer-aided Translation Tool

Over the last years, technology has achieved a dominant position in a wide range of fields, causing a profound paradigm shift in our lives. In the area of translation, technology has brought to light useful applications such as machine translation and computer-aided translation. While the former is aimed at automatically translating texts, the latter is intended to support and facilitate the translation process. In consideration of the remarkable success of translation technology, the present master’s thesis proposes a prototype for an innovative CAT tool calledTongue2Tongue which exploits state-of-the-art natural language processing techniques for enabling a wide-coverage, semantically-aware and language-independent retrieval of parallel and comparable texts. More specifically, starting from a text segment in a source language, the proposed CAT tool is capable of providing similar text segments in a target language. This function aims at facilitating the translator in understanding the content of a source text and identifying the most appropriate and adequate translations. The major innovation brought about by Tongue2Tongue consists in the implementation of innovative knowledge-based word sense disambiguation algorithms and techniques which allow to compute large-scale cross-lingual and language-independent semantic similarity among text segments. This means that Tongue2Tongue will be capable of automatically supplying parallel and comparable text segments taking into consideration the semantics of texts and regardless of the languages employed. As far as we know, this approach isbeing implemented for the first time in a CAT tool.