W
Wade Shen
Researcher at Massachusetts Institute of Technology
Publications - 7
Citations - 6519
Wade Shen is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Machine translation & Language model. The author has an hindex of 6, co-authored 7 publications receiving 6118 citations.
Papers
More filters
Proceedings ArticleDOI
Moses: Open Source Toolkit for Statistical Machine Translation
Philipp Koehn,Hieu Hoang,Alexandra Birch,Chris Callison-Burch,Marcello Federico,Nicola Bertoldi,Brooke Cowan,Wade Shen,C. Corbett Moran,Richard Zens,Chris Dyer,Ondrej Bojar,Alexandra Elena Constantin,Evan Herbst +13 more
TL;DR: An open-source toolkit for statistical machine translation whose novel contributions are support for linguistically motivated factors, confusion network decoding, and efficient data formats for translation models and language models.
Open Source Toolkit for Statistical Machine Translation: Factored Translation Models and Lattice Decoding
Philipp Koehn,Marcello Federico,Wade Shen,Nicola Bertoldi,Chris Callison-Burch,Ondrej Bojar,Brooke Cowan,Chris Dyer,Hieu Hoang,Richard Zens,Alexandra Elena Constantin,Evan Herbst,C. Corbett Moran +12 more
The JHU Workshop 2006 IWSLT System
TL;DR: A new open-source decoder is introduced that implements the state-of-the-art in statistical machine translation and results from the open-track Chinese-to-English condition are presented.
ReportDOI
A Language-Independent Approach to Automatic Text Difficulty Assessment for Second-Language Learners
TL;DR: A new baseline for language-independent text difficulty assessment applied to the Interagency Language Roundtable (ILR) proficiency scale is introduced and it is demonstrated that reading level assessment is a discriminative problem that is best-suited for regression.
Proceedings ArticleDOI
Exploiting Morphological, Grammatical, and Semantic Correlates for Improved Text Difficulty Assessment
Elizabeth Salesky,Wade Shen +1 more
TL;DR: This work demonstrates that the addition of morphological, information theoretic, and language modeling features to a traditional readability baseline greatly benefits this system's performance.