This paper describes LIUM submissions to WMT17 News Translation Task for English↔German, English↔Turkish, English→Czech and English→Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target...

Thematic progression pattern as the method of development of the text insures that the reader follows the right path in understanding the text; in this regard, this subject is attracting considerable interest among discourse analysts. This paper calls into question the status of thematic progression in the process of translating English news into Persian. With this in mind, we analyzed the them...

We describe the Cambridge University Engineering Department phrase-based statistical machine translation system for SpanishEnglish and French-English translation in the ACL 2008 Third Workshop on Statistical Machine Translation Shared Task. The CUED system follows a generative model of translation and is implemented by composition of component models realised as Weighted Finite State Transducer...

We participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs, each trained in both directions: English↔Czech, English↔German, English↔Romanian and English↔Russian. Our systems are based on an attentional encoder-decoder, using BPE subword segmentation for open-vocabulary translation with a fixed vocabulary. We experimented with usin...

This paper describes the University of Edinburgh’s submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russian, Turkish and Chinese. For the biomedical task we submitted systems for English to Czech, German, Polish and Romanian. Our systems are neural mac...

Bilingual news article alignment methods based on multilingual information retrieval have been shown to be successful for the automatic production of so-called noisy-parallel corpora. In this paper we compare the use of machine translation (MT) to the commonly used dictionary term lookup (DTL) method for Reuter news article alignment in English and Japanese. The results show the trade-off betwe...

In this paper, we describe the full-text story alignment on Chinese-English bilingual corpora of news data to mine potential parallel data for machine translation. Several standard information retrieval methods are tested and two translation-model based alignment models are proposed and studied. Modeling the process of generating the parallel English story from Chinese story gives significant i...

For NTCIR Workshop 5 UC Berkeley participated in the bilingual task of the CLIR track. Our focus was on Chinese topic searches against the Japanese News document collection, and on Japanese topic search against the Chinese News Document Collection. Extending our work of NTCIR 4 workshop, we performed search experiments to segment and use Chinese search topics directly as if they were Japanese t...

Metaphorical expressions (MEs) are abundant in political text and their translation ‎poses challenges particularly for retaining the implicit meaning. This research focuses on examining use of conceptual metaphors (CMs) ‎in Indonesian ‎political news English translation. The objectives ‎ to identify types source domain CMs explain how translated.‎ ‎Grounding mixed-methods, data were metaphorica...