Material Detail

This video was recorded at European Summer School in Logic, Language and Information. People use natural language and write texts to express themselves. For the purpose of text processing, text can be represented in different ways ranging from simply characters to capturing knowledge from the text in a form of logic. One of the key properties of natural languages is redundancy in the encoded information and the structure used. As a consequence, different techniques can extract different aspects of information from text. They range from simple techniques, such as character counting, to more sophisticated, such as linear algebra, to the advanced techniques which exploit the structural aspects of text. Many of these techniques deliver something useful and solve somebody's problem. Examples of such problems are: language identification (solved with character counting), document categorization (solved with linear algebra methods), question-answering (solved typically with shallow linguistic methods), and reasoning (solved typically using logic). The talk will present different text representations from the view of automatic text processing. In the second half of the talk we will take a look at some research results based on using machine learning methods and we will see demos of the corresponding prototype systems.

Disciplines:

• Science and Technology  / Computer Science