A Hybrid Statistical and Rule-Based Natural Language Processing Chain for Portuguese

From HLT@INESC-ID

Nuno Mamede

Date

  • 15:00, Friday, January 11th, 2013
  • Room 336

Speaker

Abstract

STRING has a modular structure and performs all basic text processing tasks, namely: (i) tokenization and text segmentation, (ii) part-of-speech tagging, (iii) morphosyntactic disambiguation, (iv) shallow parsing (chunking), and (v) deep parsing (dependency extraction). The STRING architecture and recent developments will be presented.