An Hybrid Statistical and Rule-Based Natural Language Processing Chain for Portuguese: Difference between revisions
From HLT@INESC-ID
(Created page with "__NOTOC__ {{infobox|name=Nuno Mamede |username=njm |contact=njm |phone=+351-213-100-367 |fax=+351-213-145-843 }} == Date == * 15:00, Friday, January 11<sup>th</sup>, 2013 * Roo...") |
(No difference)
|
Revision as of 16:18, 14 January 2013
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.