Natural Language Processing

I am a member of the Natural Language Processing Research Group at UPC.

Here you can find some useful stuff for NLP, as well as some links to some interesting projects I am currently --or have been recently-- involved in.

Some interesting projects

• Text processing
  • FreeLing: An open-source suite of language analyzers
  • Treeler: Library of structure prediction methods, focusing on Natural Language Processing tasks.
• Language Understanding and Knowledge Extraction
  • XLike: Cross-Lingual Knowledge Extraction.
  • SKATER: Scenario Knowledge Acquisition by Textual Reading.
• Machine Translation
  • FAUST: Feedback Analysis for User Adaptive Statistical Translation
  • MOLTO: Multilingual On-Line Translation

Some useful things

• List of English empty words
• List of Catalan empty words
• List of Spanish empty words
• Another list of Spanish empty words
• Several frequency counts of word forms, lemmas, and PoS from a 5.5 milion word Spanish corpus of unrestricted text.
• Word form frequency counts from 1.1 Mw of WSJ corpus.

• Unix for Poets by K.W.Church