This paper describes efforts towards the development of an Arabic to Italian SMT system for the news domain. Since only very little parallel data are available for this language pair, we investigated both the exploitation of comparable corpora and pivot translation. Experimental evaluation was conducted on a new benchmark developed by extending two Arabic-to-English NIST evaluation sets. Prelim...

This paper explores the news trustworthiness and media credibility of The Economist’s news report on 9 July 2009, and the communicative roles of 846 readers’ responses. Theoretically guided by news translation and cultural resistance and the online public sphere, we applied online field observation and discourse analysis and achieved two main findings: First, although the news report covered th...

This paper documents an undergraduate course at Hunter College, in which one instructor, six undergraduates, and one high school student built 17 machine translation systems in six months from scratch. The team successfully participated in the second Conference on Machine Translation (WMT17) evaluation on the news task in Finnish-English and Latvian-English and on the bio-medical task in French...

This paper presents an ongoing work on identifying similarity between documents across News papers in different languages. Our aim is to identify similar documents for a given News or event as a query, across languages and make cross lingual search more accurate and easy. For example given an event or News in English, all the English news documents related to the query are retrieved as well as ...

What is the role of textual features above the sentence level in advancing the machine translation of literature? This paper examines how referential cohesion is expressed in literary and non-literary texts and how this cohesion affects translation. We first show in a corpus study on English that literary texts use more dense reference chains to express greater referential cohesion than news. W...

We propose a new approach to recognize objects and scenes in news videos motivated by the availability of large video collections. This approach considers the recognition problem as the translation of visual elements to words. The correspondences between visual elements and words are learned using the methods adapted from statistical machine translation and used to predict words for particular ...