Difference between revisions of "Text Simplification - State of Art"

From HLT@INESC-ID

Line 18: Line 18:
 
== Abstract ==
 
== Abstract ==
  
In this talk, I will be reviewing the literature about text simplification. I will also describe some of my initial and current work in text simplification with educational purposes. This talk will be given to fulfill the Natural Language Processing Project course requirements.
+
Text simplification is a field that can be useful for many applications because it can improve text readability and help in NLP tasks. Thus, I will give a brief overview about this field. Then, I will talk about the specific problem that we are trying to solve, which is the creation of a text simplification system with educational purposes. We have the simplification of Geography and History texts of 7 th to 8th written in Portuguese to 3 th and 4 th graders as initial goal. Given the complexity of this problem, we decided to break it into subtasks. Hence, we are exploring ways of performing the most frequent syntactic simplification: splitting sentences.  I will also discuss about the initial work, such as the creation of simplified corpora, adaptation/creation of splitting sentence classifiers and I will compare with similar work developed for English and Brazilian Portuguese.
 
+
  
 
'''Note:''' This seminar will be held in English, if required.
 
'''Note:''' This seminar will be held in English, if required.

Revision as of 15:11, 24 November 2010

Luís Marujo

Date

  • 15:00, Friday, November 26th, 2010
  • Room 336

Speaker

Abstract

Text simplification is a field that can be useful for many applications because it can improve text readability and help in NLP tasks. Thus, I will give a brief overview about this field. Then, I will talk about the specific problem that we are trying to solve, which is the creation of a text simplification system with educational purposes. We have the simplification of Geography and History texts of 7 th to 8th written in Portuguese to 3 th and 4 th graders as initial goal. Given the complexity of this problem, we decided to break it into subtasks. Hence, we are exploring ways of performing the most frequent syntactic simplification: splitting sentences. I will also discuss about the initial work, such as the creation of simplified corpora, adaptation/creation of splitting sentence classifiers and I will compare with similar work developed for English and Brazilian Portuguese.

Note: This seminar will be held in English, if required.