Changes between Version 6 and Version 7 of private/AdvancedNlpCourse/InformationExtraction


Ignore:
Timestamp:
Sep 2, 2015 11:13:35 AM (4 years ago)
Author:
xkovar3
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • private/AdvancedNlpCourse/InformationExtraction

    v6 v7  
    55Prepared by: Vojtěch Kovář
    66
    7 == TODO til 31.5.2015 ==
    8 
    9  1. choose particular papers for [[#References|References]] below (that will serve as input for the lecture later on)
    10  1. prepare the [[#PracticalSession|Practical Session]]
    117
    128== State of the Art ==
     
    3127== Practical Session ==
    3228
    33 You are given several [attachment:wiki.txt short excerpts from Czech wikipedia] as a plain text. They were analyzed by automatic sentence detection, tokenization (unitok tool), morphological analysis and tagging (desamb tool), and syntactic analysis (SET tool, with --long-phrases option) and [attachment:wiki.phrases this is the result].
     29You are given few [attachment:wiki.txt short excerpts from Czech wikipedia] as a plain text. They were analyzed by automatic sentence detection, tokenization (unitok tool), morphological analysis and tagging (desamb tool), and syntactic analysis (SET tool, with --long-phrases option) and [attachment:wiki.phrases this is the result].
    3430
    3531Write a short program in Python which will extract simple information about who was who, from the parsed file. The result should look like [attachment:wiki.output this file].