J
James Cross
Researcher at Facebook
Publications - 65
Citations - 1619
James Cross is an academic researcher from Facebook. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 18, co-authored 58 publications receiving 1092 citations. Previous affiliations of James Cross include University of Washington & City University of New York.
Papers
More filters
Journal ArticleDOI
No Language Left Behind: Scaling Human-Centered Machine Translation
Nllb team,Marta R. Costa-jussà,James Cross,Onur cCelebi,Maha Elbayad,Kenneth Heafield,Kevin Heffernan,Elahe Kalbassi,Janice Si-Man Lam,Daniel Licht,Jean Maillard,Anna Sun,Skyler Wang,Guillaume Wenzek,Alison Youngblood,Bapi Akula,Loïc Barrault,Gabriel Mejia Gonzalez,Prangthip Hansanti,John Hoffman,Semarley Jarrett,Kaushik Ram Sadagopan,Dirk Rowe,Shannon Spruit,Chau Tran,Pierre Andrews,Necip Fazil Ayan,Shruti Bhosale,Sergey Edunov,Angela Fan,Cynthia Gao,Vedanuj Goswami,Francisco Guzm'an,Philipp Koehn,Alexandre Mourachko,Christophe Ropers,Safiyyah Saleem,Holger Schwenk,Jeff Wang +38 more
TL;DR: A conditional compute model based on Sparsely Gated Mixture of Experts that is trained on data obtained with novel and effective data mining techniques tailored for low-resource languages is developed, laying important groundwork towards realizing a universal translation system.
Journal ArticleDOI
Exploring the Political Agenda of the European Parliament Using a Dynamic Topic Modeling Approach
Derek Greene,James Cross +1 more
TL;DR: The authors analyzed the political agenda of the European Parliament (EP) plenary, how it has evolved over time, and the manner in which MEPs have reacted to external and internal stimuli when making plenary speeches.
Proceedings ArticleDOI
Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles.
James Cross,Liang Huang +1 more
TL;DR: This article proposed a shift-reduce system whose stack contains merely sentence spans, represented by a bare minimum of LSTM features, which achieves the best F1 scores on both English and French of any parser that does not use re-ranking or external data.
Journal ArticleDOI
A new dataset on decision-making in the European Union before and after the 2004 and 2007 enlargements (DEUII)
Robert Thomson,Javier Arregui,Dirk Leuffen,Rory Costello,James Cross,Robin Hertz,Thomas Elbenhardt Jensen +6 more
TL;DR: A new dataset on decision-making in the European Union (DEUII) is presented that revises and expands a previous dataset and identifies its relevance to several research agendas in EU studies.
Proceedings ArticleDOI
Incremental Parsing with Minimal Features Using Bi-Directional LSTM
James Cross,Liang Huang +1 more
TL;DR: The authors used bi-directional LSTM sentence representations to model a parser state with only three sentence positions, which automatically identifies important aspects of the entire sentence and achieved state-of-the-art results among greedy dependency parsers for English.