Benjamin P. Wellington
Email: {lastname}@cs.nyu.edu
Current Research
I'm currently doing research at Two Sigma Investments. Interested? Email me: ben.mylastname@twosigma.com
Prior Research
I worked with Professor I. Dan Melamed on Machine Translation. More specifically my interests include empirical methods for machine translation, grammar formalisms, MT evaluation, MT system design and implementation, efficient biparsing and discontinuous constituent parsing. My work was part of the Proteus Project at NYU.
Publications
Benjamin Wellington, Joseph Turian, and I. Dan Melamed (2009).
Towards Purely Discriminative Training for Tree-Structured Translation Models.
[PS][PDF]In: Cyril Goutte, Nicola Cancedda, Marc Dymetman, and George Foster.
Learning Machine Translation. MIT Press. pp. 131-149.
Benjamin Wellington (2007) . Tree-Structured Models of Multitext: Theory, Design and Experiments, Ph.D. Dissertation, New York University.
[PS][PDF]
Joseph Turian, Benjamin Wellington, and I. Dan Melamed (2006).
Scalable Discriminative Learning for Natural Language Parsing and Translation, to appear in the Proceedings of the 20th Annual Conference on Neural Information Processing Systems (NIPS-06), Vancouver, BC.
Benjamin Wellington, Joseph Turian, Chris Pike, and I. Dan Melamed (2006).
Scalable Purely-Discriminative Training for Word and Tree Transducers,.
[PS][PDF]
7th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-06), Boston, MA.
Benjamin Wellington, Sonjia Waxmonsky, I. Dan Melamed. Empirical Lower Bounds on the Complexity of Translational Equivalence,
[PS][PDF]
Proceedings of the 44th Annual Conference of the Association for Computational Linguistics (ACL-06), Sydney, Australia
A. Burbank, M. Carpuat, S. Clark, M. Dreyer, P. Fox, D. Groves, K. Hall, M. Hearne, I. D. Melamed, Y. Shen, A. Way, B. Wellington, and D. Wu Final Report of the 2005 Language Engineering Workshop on Statistical Machine Translation by Parsing, [PDF] November, 2005
Benjamin Wellington, I. Dan Melamed, Wei Wang. GenPar: An open-source toolkit for machine translation by parsing (in C++).[website] New York University, May 2005.
I. Dan Melamed, Giorgio Satta, and Ben Wellington
(2004). Generalized Multitext Grammars[PS][PDF] Proceedings of the 42nd
Annual Conference of the Association for Computational
Linguistics (ACL-04), Barcelona, Spain. This version has a couple of typos corrected.
Curriculum Vitae
My (outdated) curriculum vitae is available in pdf and ps forms.
Other Projects
I am working with some amazing people to get a new non-profit off of the ground called New Rust Exchange. It focuses on using improvisation and improv comedy as a teaching tool for life skills.
Comedy
With over 12 years of directing/performing experience, I am available to teach/coach/perform improv comedy. See what others have said about my work here.
