Projects

Research

Current

  • Member of the program “Métodos Empíricos Avanzados para Procesamiento del Lenguaje Natural”. Financiado por SECyT, UNC. 2016 – 2017.
  • Director of the project “Algoritmos Espectrales para el Análisis Sintáctico de Lenguaje Natural”. Funded by SECyT, UNC. 2016 – 2017.
  • Director of the project PICT 2014-1651 “Algoritmos Espectrales para el Análisis Sintáctico de Lenguaje Natural”. Funded by the National Agency of Scientific and Technological Promotion of Argentina (ANPCyT). 2015 – 2017.

Previous

  • Member of the international project “RITA: RIch Text Analysis through Enhanced Tools based on Lexical Resources”. Participants: NLP Group (UNC, Ar), NLIP (UFRGS, Br), LaLiC (UFSCar, Br), NLP Group (UdelaR, Uy), ModyCo (U-Paris10, Fr), CL Group (UPEM, Fr). Funded by STIC-AmSud program. 2014 – 2015.
  • Director of the project “Análisis sintáctico semi-supervisado de lenguaje natural” (“Semi-supervised natural language parsing”). Academically endorsed by SECyT, UNC. 2012 – 2013.
  • Member of the program 05/BP05 “Análisis Sintáctico de Lenguaje Natural: Recursos, Técnicas y Aplicaciones”. Funded by SECyT, UNC. 2012 – 2013.
  • Member of the project “Enriquecimiento de un Léxico Verbal Orientado a Aplicaciones de Procesamiento del Lenguaje Natural”. Funded by SECyT, UNC. 2012 – 2013.
  • Member of the project PICT 2007-02290 “Minería de datos en texto semi-estructurado” (“Data mining in semi-structured text”). Funded by ANPCyT. 2010 – 2012.
  • Member of the project “Aprendizaje no supervisado de estructuras sintácticas” (“Unsupervised learning of syntactic structures”). Funded by SECyT, UNC. 2010 – 2011.
  • Member of the project 05/B408 “Análisis sintáctico del español” (“Syntactic analysis of spanish”). Funded by SECyT, UNC. 2008 – 2009.
  • Member of the project PICT 2006-00969 “Aprendizaje automático de lenguajes complejos” (“Automatic learning of complex languages”). Funded by ANPCyT. 2007 – 2009.

francolq @ GitHub

IEPY

Project homepage

IEPY is a framework for doing information extraction on unstructured documents. It uses partially supervised machine learning techniques (i.e., there's a human helping the application, but the application generalizes what the human does and learns).


Implementation of the DMV+CCM Parser

Project homepage

Implementations of the CCM, DMV and DMV+CCM parsers from Klein and Manning (2004), and code for testing them with the WSJ, Negra and Cast3LB corpora (English, German and Spanish respectively).


HOWTOS

Notes about the usage of some programs:

Only in Spanish for the moment:


Simulador de Impacto Ganancial

Fluxus

Sometimes I play a bit with this software for live programming of visual things that respond to music or other stimulus. It uses a Lisp-style programming language and the source code is shown on top of the images so the public can see how they are built.

More...


reacTIVision