• Publications
  • Influence
Fast and Robust Neural Network Joint Models for Statistical Machine Translation
Recent work has shown success in using neural network language models (NNLMs) as features in MT systems. Here, we present a novel formulation for a neural network joint model (NNJM), which augmentsExpand
  • 468
  • 67
The iLab Shared Architecture: A Web Services Infrastructure to Build Communities of Internet Accessible Laboratories
The Massachusetts Institute of Technology's iLab project has developed a distributed software toolkit and middleware service infrastructure to support Internet-accessible laboratories and promoteExpand
  • 383
  • 19
Segmentation for English-to-Arabic Statistical Machine Translation
In this paper, we report on a set of initial results for English-to-Arabic Statistical Machine Translation (SMT). We show that morphological decomposition of the Arabic source is beneficial,Expand
  • 74
  • 14
Machine Translation of Arabic Dialects
Arabic Dialects present many challenges for machine translation, not least of which is the lack of data resources. We use crowdsourcing to cheaply and quickly build Levantine-English andExpand
  • 143
  • 13
Factored Soft Source Syntactic Constraints for Hierarchical Machine Translation
This paper describes a factored approach to incorporating soft source syntactic constraints into a hierarchical phrase-based translation system. In contrast to traditional approaches that directlyExpand
  • 14
  • 4
Syntactic Phrase Reordering for English-to-Arabic Statistical Machine Translation
Syntactic Reordering of the source language to better match the phrase structure of the target language has been shown to improve the performance of phrase-based Statistical Machine Translation. ThisExpand
  • 34
  • 2
Neural-Network Lexical Translation for Cross-lingual IR from Text and Speech
We propose a neural network model to estimate word translation probabilities for Cross-Lingual Information Retrieval (CLIR). The model estimates better probabilities for word translations thanExpand
  • 11
  • 2
Systematic Comparison of Professional and Crowdsourced Reference Translations for Machine Translation
We present a systematic study of the effect of crowdsourced translations on Machine Translation performance. We compare Machine Translation systems trained on the same data but with translationsExpand
  • 11
  • 2
Statistical Machine Translation Features with Multitask Tensor Networks
We present a three-pronged approach to improving Statistical Machine Translation (SMT), building on recent success in the application of neural networks to SMT. First, we propose new features basedExpand
  • 15
Improved morphological decomposition for Arabic broadcast news transcription
We show the progress for Arabic speech recognition by incorporating contextual information into the process of morphological decomposition. The new approach achieves lower out-of-vocabulary and wordExpand
  • 15