This paper described our handheld two-way speech translation system for English and Iraqi. The focus is on developing a field usable handheld device for speech-to-speech translation. The computation and memory limitations on the handheld impose critical constraints on the ASR, SMT, and TTS components. In this paper we discuss our approaches to optimize these components for the handheld device and present performance numbers from the evaluations that were an integral part of the project. Since one major aspect of the TransTac program is to build fieldable systems, we spent significant effort on developing an intuitive interface that minimizes the training time for users but also provides useful information such as back translations for translation quality feedback.

The problem of managing an effective relationship between course staff and students in large programming courses admits no trivial solution. Students often complain of lack of feedback, slow assignment grading times, and a gap in communication between them and the course staff responsible for evaluating their work. In addition, course staff feels powerless to help because of the complexity and sheer numbers of students involved in such courses. In this paper, we describe our Web-based distributed application, FrontDesk that attempts to bridge the feedback and communication gap that these courses suffer from. FrontDesk provides tools for students to submit their work through the Web and to receive rich, informative feedback. It provides course staff with the ability to give effective subjective feedback for large courses and to automate objective programming assignment correctness testing in a flexible, distributed, and efficient manner.

Phrase level translation models are effective in improving translation quality by addressing the problem of local re-ordering across language boundaries. Methods that attempt to fundamentally modify the traditional IBM translation model to incorporate phrases typically do so at a prohibitive computational cost. We present a technique that begins with improved IBM models to create phrase level knowledge sources that effectively represent local as well as global phrasal context. Our method is robust to noisy alignments at both the sentence and corpus level, delivering high quality phrase level translation pairs that contribute to significant improvements in translation quality (as measured by the BLEU metric) over word based lexica as well as a competing alignment based method.

In this paper we describe the components of our statistical machine translation system. This system combines phrase-to-phrase translations extracted from a bilingual corpus using different alignment approaches. Special methods to extract and align named entities are used. We show how a manual lexicon can be incorporated into the statistical system in an optimized way. Experiments on Chinese-to-English and Arabic-to-English translation tasks are presented.