We describe the machine translation systems developed at the National Research Council of Canada (NRC) for the RussianEnglish and Chinese-English news translation tasks of the Second Conference on Machine Translation (WMT 2017). We conducted several experiments to explore the best baseline settings for neural machine translation (NMT). In the RussianEnglish task, to our surprise, our bestperfor...

We present a comparative evaluation of two data-driven models used in translation selection of English-Korean machine translation. Latent semantic analysis(LSA) and probabilistic latent semantic analysis (PLSA) are applied for the purpose of implementation of data-driven models in particular. These models are able to represent complex semantic structures of given contexts, like text passages. G...

Reports on what users experience when interacting with currently available news aggregator services. Five news aggregator services were chosen as the most representatives of emerging trends in this area of research and a combination of quantitative and qualitative methods were used for data collection involving users from the academic and research community. Forty-five responses were received f...

Purpose: The aim of present research was the comparative study of white marriage news based on effective news components in the Persian section of Al-Alam, Persian BBC and Voice of America news sites. Methodology: This study in terms of purpose was applied and in terms of implementation method was quantitative. The research community was the white marriage news of Persian section of Al-Alam, P...

The primary objective of our work is to build a large-scale English-Thai dataset for machine translation. We construct an translation with over 1 million segment pairs, curated from various sources, namely news, Wikipedia articles, SMS messages, task-based dialogs, web-crawled data and government documents. Methodology gathering data, building parallel texts removing noisy sentence pairs are pr...

The success of statistical language modeling techniques is crucially dependent on the availability of a large amount training text. For a language in which such large text collections are not available, methods have recently been proposed to take advantage of a resource-rich language, together with cross-lingual information retrieval and machine translation, to sharpen language models for the r...

Multilingual corpora are valuable resources for cross-language information retrieval and are available in many language pairs. However the Persian language does not have rich multilingual resources due to some of its special features and difficulties in constructing the corpora. In this study, we build a Persian-English comparable corpus from two independent news collections: BBC News in Englis...

News articles in different languages on the same event are invaluable for analyzing standpoints and viewpoints in different countries. The major challenge to identify such closely related bilingual news articles is how to take full advantage of various information sources such as length, translation equivalence and publishing date. Accordingly, we propose a discriminative model for bilingual ne...

In this paper we investigate the automatic collection, generation and evaluation of sentential paraphrases. Valuable sources of paraphrases are news article headlines; they tend to describe the same event in various different ways, and can easily be obtained from the web. We describe a method for generating paraphrases by using a large aligned monolingual corpus of news headlines acquired autom...