To overcome the scarceness of bilingual corpora for some language pairs in machine translation, pivot-based SMT uses pivot language as a "bridge" to generate source-target translation from sourcepivot and pivot-target translation. One of the key issues is to estimate the probabilities for the generated phrase pairs. In this paper, we present a novel approach to calculate the translation probabi...

We investigate how to improve bilingual embedding which has been successfully used as a feature in phrase-based statistical machine translation (SMT). Despite bilingual embedding’s success, the contextual information, which is of critical importance to translation quality, was ignored in previous work. To employ the contextual information, we propose a simple and memory-efficient model for lear...

We prove that the symbolic dynamical system generated by a purely substitutive Arnoux-Rauzy sequence is measurably conjugate to a toral translation. The proof is based on an explicit construction of a fundamental domain with fractal boundary (a Rauzy fractal) for this toral translation. Communicated by Pierre Liardet Dedicated to the memory of Gérard Rauzy

This paper introduces a machine learning approach to distinguish machine translation texts from human texts in the sentence level automatically. In stead of traditional methods, we extract some linguistic features only from the target language side to train the prediction model and these features are independent of the source language. Our prediction model presents an indicator to measure how m...

We build upon recent work by Baral, Dzifcal and Son that define the translation into ASP of (some classes of) natural language sentences from the lambda-calculus intermediate format generated by CCG grammars. We propose to use SE-DCG grammars, and we introduce automatic generation of lambda-calculus expressions from template ones, thus improving the effectiveness and generality of the translation

This paper describes a vision-based technique for the detection of moving objects by a moving airborne vehicle. The technique, which is based on measurement of optic flow, computes the egomotion of the aircraft based on the pattern of optic flow in a panoramic image, then determines the component of this optic flow pattern that is generated by the aircraft’s translation, and finally detects the...

In the formally syntax-based MT, a hierarchical tree generated by synchronous CFG rules associates the source sentence with the target sentence. In this paper, we propose a source dependency model to estimate the probability of the hierarchical tree generated in decoding. We develop this source dependency model from word-aligned corpus, without using any linguistically motivated parsing. Our ex...

We investigate the problem of combining the outputs of different translation systems into a minimum Bayes’ risk consensus translation. We explore different risk formulations based on the BLEU score, and provide a dynamic programming decoding algorithm for each of them. In our experiments, these algorithms generated consensus translations with better risk, and more efficiently, than previous pro...

We build upon recent work by Baral, Dzifcak and Son that define the translation into ASP of (some classes of) natural language sentences from the lambda-calculus intermediate format generated by CCG grammars. We introduce automatic generation of lambda-calculus expressions from template ones, thus improving the effectiveness and generality of the translation process.

In the past decade, in vitro transcription/translation technologies have emerged as discovery tools for screening large protein expression libraries, for the selection of engineered polypeptide libraries, and as alternatives to conventional heterologous expression for protein production. Therapeutic proteins and peptides discovered using ribosome-based display methods that link genetic informat...