We explore how to improve machine translation systems by adding more translation data in situations where we already have substantial resources. The main challenge is how to buck the trend of diminishing returns that is commonly encountered. We present an active learning-style data solicitation algorithm to meet this challenge. We test it, gathering annotations via Amazon Mechanical Turk, and f...

An important task of pattern recognition is identifying or synthesizing stylistic variations on a signal independently of its underlying content [Omohundro 1995; Hofstadter 1995; Tenenbaum and Freeman 2000; Brand and Hertzmann 2000; Rose et al. 1998]. For example, one may want to differentiate stylistic variations in handwriting from the underlying content, or letters. We study this problem for...

background this article tries to determine some cases of arabicism in medical texts, through citing evidence from some persian medical texts and also tries to show their significant role in the process of correction, translation, and the revision of the ancient medical texts and its ensuing research and writing of new works based on the old ones. the importance of arabicism in medical text is t...

This paper describes NTT SMT System 2008 presented at the patent translation task (PAT-MT) in NTCIR-7. For PAT-MT, we submitted our strong baseline system faithfully following a hierarchical phrasebased statistical machine translation [2]. The hierarchical phrase-based SMT is based on a synchronousCFGs in which a paired source/target rules are synchronously applied starting from the initial sym...

In statistical machine translation, decoding without any reordering constraint is an NP-hard problem. Inversion Transduction Grammars (ITGs) exploit linguistic structure and can well balance the needed flexibility against complexity constraints. Currently, translation models with ITG constraints usually employs the cube-time CYK algorithm. In this paper, we present a shift-reduce decoding algor...

Example-based machine translation (EBMT) is a promising translation method for speechto-speech translation because of its robustness. It retrieves example sentences similar to the input and adjusts their translations to obtain the output. However, it has problems in that the performance degrades when input sentences are long and when the style of inputs and that of the example corpus are differ...

Several technological applications require the translation of a protein into a nucleic acid that codes for it (“backtranslation”). The degeneracy of the genetic code makes this translation ambiguous; moreover, not every translation is equally viable. The common answer to this problem is the imitation of the codon usage of the target species. Here we discuss several other features of coding sequ...