|
Enrique Henestroza Anguiano ehenestroza à gmail point com |
|
|
Background I was a PhD student in computer science and linguistics at Université Paris Diderot, where my advisors were Laurence Danlos, Alexis Nasr, and Marie Candito. I was part of the Alpage project team, a collaboration between INRIA and Université Paris Diderot, which conducts research in natural language processing. In addition, I took part in the SEQUOIA research project, whose goal was to achieve large-scale, statistical syntactic parsing for French. My research interests include natural language processing, computational linguistics, machine learning, statistical dependency parsing, and distributional lexical semantics. |
|
|
Publications Efficient Large-Context Dependency Parsing and Correction with Distributional Lexical Resources
2012 Probabilistic lexical generalization for French dependency parsing
Ubiquitous usage of a broad coverage French corpus: Processing the Est Republicain corpus
2011 A word clustering approach to domain adaptation: Effective parsing of biomedical texts
Parse correction with specialized models for difficult attachment types
FreDist: Automatic construction of distributional thesauri for French
2010 Benchmarking of statistical dependency parsers for French
Previous Simultaneous multilingual search for translingual information retrieval
|
|
|
Presentations Mesures d'association lexicale pour
le traitement d'attachement des groupes prépositionnels
dans l'analyse syntaxique statistique du français.
Parse correction with specialized
models for difficult attachment types.
|
|
|
Research Code FreDist: A Python package implementing methods that integrate transition-based dependency parsing, neighborhood parse correction, and the extraction of distributional lexical resources that can be used as features in parsing models. [tgz] |
|
| Last Updated: July 2nd, 2013 | |