In a multi script environment, majority of the documents may contain text information printed in more than one script/language. For automatic processing of such documents through Optical Character Recognition (OCR), it is necessary to identify different script regions of the document. In this paper, it is proposed to develop a model to identify the script type of a trilingual document printed i...

Explaining why the same passage may have different rhetorical structures when conveyed in different languages remains an open question. Starting from a trilingual translation corpus, this paper aims to provide a new qualitative method for the comparison of rhetorical structures in different languages and to specify why translated texts may differ in their rhetorical structures. To achieve these...

Current neural machine translation (NMT) usually extracts a fixedlength semantic representation for source sentence, and then depends on this representation to generate corresponding target translation. In this paper, we proposed a pivot-based semantic splicing model (PBSSM) to obtain a semantic representation including more translation information for source sentence, thus improving the transl...

Word retrieval deficits for specific grammatical categories, such as verbs versus nouns, occur as a consequence of brain damage. Such deficits are informative about the nature of lexical organization in the human brain. This study examined retrieval of grammatical categories across three languages in a trilingual person with aphasia who spoke Arabic, French, and English. In order to delineate t...

This presentation describes a trilingual corpus of three endangered languages of the Kiranti group (Tibeto-Burman family) from Eastern Nepal. The languages, which are exclusively oral, share a rich mythology, and it is thus possible to build a corpus of the same native narrative material in the three languages. The segments of similar semantic content are tagged with a "similarity" label to ide...

This paper describes the design and development of a trilingual spontaneous speech corpus for statistical speech-to-speech translation. The languages considered are Catalan, Spanish and US-English. This corpus has been built bearing in mind the strong need for multilingual collections of on-line data within the area of statistical translation, as well as the need for data that are parallel or a...