I am available for consulting on machine learning and natural language processing.
Try out Training Examples, a machine learning and natural language processing Q&A site!
|
Work address (physical)
2920 Chemin de la Tour Montréal, Québec, Canada, H3T 1J4 |
Work address (mail):
|
Joseph Turian, Lev Ratinov, and Yoshua Bengio (2010).
Word representations: A simple and general method for semi-supervised learning.
[PDF]
[PPT]
Association for Computational Linguistics (ACL), Uppsala, Sweden.
James Bergstra, Olivier Breuleux, Frederic Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Desjardins, Joseph Turian, and Yoshua Bengio (2010).
Theano: a CPU and GPU Math Expression Compiler.
[PDF]
Proceedings of the Python for Scientific Computing Conference (SciPy).
Hugo Larochelle, Yoshua Bengio, and Joseph Turian (2010).
Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest.
[PDF]
Neural Computation 22, pp. 2285-2307.
Giuseppe Attardi, Feliec Dell'Orletta, Maria Simi, and Joseph Turian (2009).
Accurate Dependency Parsing with a Stacked Multilayer Perceptron.
Proceeding of EVALITA 2009.
Note: Our parser achieved the best score in both the Main and Pilot subtask.
Joseph Turian, Lev Ratinov, Yoshua Bengio, and Dan Roth (2009).
A preliminary evaluation of word representations for named-entity recognition.
[PDF]
NIPS Workshop on Grammar Induction, Representation of Language and Language Learning, Vancouver, BC.
Joseph Turian, James Bergstra and Yoshua Bengio (2009).
Quadratic Features and Deep Architectures for Chunking.
[PDF]
North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) 2009, Boulder, CO.
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.
Joseph Turian (2007).
Constituent Parsing by Classification.
[PS.GZ]
[PDF]
Ph.D. thesis, New York University, New York, NY.
Advisor: I. Dan Melamed.
Committee:
Michael Collins,
Ralph Grishman,
Mehryar Mohri, and
Satoshi Sekine.
Joseph Turian, Benjamin Wellington, and I. Dan Melamed (2007).
Scalable Discriminative Learning for Natural Language Parsing and Translation.
[PS]
[PDF]
20th Annual Conference on Neural Information Processing Systems (NIPS 19), 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.
The relevant software, GenPar, is publicly available.
Joseph Turian and I. Dan Melamed (2006).
Advances in Discriminative Parsing.
[PS]
[PDF]
Conference of the International Committee on Computational Linguistics
and the Association for Computational Linguistics (COLING/ACL), Sydney,
Australia.
The relevant software is publicly available.
Joseph Turian and I. Dan Melamed (2006).
Computational Challenges in Parsing by Classification.
[PS]
[PDF]
HLT-NAACL Workshop on Computationally Hard Problems and Joint Inference
in Speech and Language Processing, New York, NY.
Joseph Turian and I. Dan Melamed (2005).
Constituent Parsing by Classification.
[PS]
[PDF]
9th International Workshop on Parsing Technologies (IWPT), Vancouver, BC.
Joseph Turian, Luke Shen, and I. Dan Melamed (2003).
Evaluation of Machine Translation and its Evaluation.
[PS]
[PDF]
Proteus technical report #03-005, a revised version of the paper
presented at MT Summit IX, New Orleans, LA.
The relevant software, GTM,
is publicly available.
I. Dan Melamed, Ryan Green and Joseph Turian (2003).
Precision and Recall of Machine Translation.
[PS]
[PDF]
Proteus technical report #03-004, a revised version of the paper
presented at HLT-NAACL 2003, Edmonton, AB.