This paper describes the neural and phrase-based machine translation systems submitted by CUNI to English-Czech News Translation Task of WMT17. We experiment with synthetic data for training and try several system combination techniques, both neural and phrase-based. Our primary submission CU-CHIMERA ends up being phrase-based backbone which incorporates neural and deep-syntactic candidate tran...

pain is a phenomenon experienced more or less by all people during their lives. since sufferers usually use language as the most important human communication tool to inform others about their pains, sentences describing pain and studying them linguistically may reveal some points. in this paper, after a short introduction to the subject and reviewing the literature, we take one of the systemat...

ed from: Conkly, D., Novac, E., Boissy, A. Bethoux, F., & Chemali, K. (2012). The effects of modified melodic intonation therapy on nonfluent aphasia: A pilot study. Journal of Speech, Language, and Hearing Research, 55, 1462–1471. Source of funding and disclosure of interest: The research project was internally funded; no external funding was reported. The authors reported no conflicts of inte...

We present a new open source toolkit for phrase-based and syntax-based machine translation. The toolkit supports several state-of-the-art models developed in statistical machine translation, including the phrase-based model, the hierachical phrase-based model, and various syntaxbased models. The key innovation provided by the toolkit is that the decoder can work with various grammars and offers...

This paper describes statistical machine translation improved by applying hierarchical phrase alignment. The hierarchical phrase alignment is a method to align bilingual sentences phrase-by-phrase employing the partial parse results. Based on the hierarchical phrase alignment, a translation model is trained on a chunked corpus by converting hierarchically aligned phrases into a sequence of chun...

Objective: To develop a document indexing scheme that improves the retrieval effectiveness of free-text medical documents. Design: The phrase-based vector space model (VSM) uses multi-word phrases as indexing terms. Each phrase consists of a concept in the unified medical language system (UMLS) and its corresponding component word stems. The similarity between concepts are defined by their rela...

Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using this cost to rerank the n-best NMT outputs. The main ...