NATURAL
LANGUAGE PROCESSING
ECTS: 6
Lecturers: Ana García-Serrano, Igor Boguslavsky
Goals:
§
Familiarize the
students with the state-of-the-art and challenges of natural language
processing.
§
Initiate the
students into the basic techniques of the computational analysis of natural
language at different levels of the language structure.
Description
Natural
language processing (NLP) is a subfield of artificial intelligence and computational linguistics.
Artificial intelligence provides models of cognitive processes, knowledge
representation languages and methods for their processing. Computational
linguistics is mostly concerned with modeling various aspects of human
abilities connected with natural language. NLP focuses on the practical issues.
Its goal is to create software products that have some knowledge of human
language. Such products are going to change our lives. They are urgently needed
for improving human-machine interaction since the main obstacle in the
interaction between human and computer is a communication problem. The
objective of the NLP activity is to design and build software that will
analyze, understand, and generate languages that humans use naturally, so that
eventually we will be able to address computers as though we were addressing another
person. On the other hand, NLP is essential in overcoming the language barrier
between humans. Although existing systems are far from achieving human ability,
they have numerous possible applications motivated by the new and ever
increasing market requirements: machine translation for on-line services, advanced
human-machine interaction, information retrieval and information extraction on the web, data mining and
information summarization, etc.
In this course, we will
present methods of representing and processing various types of knowledge relevant
for NLP. We will familiarize the students with different NLP applications,
their functionalities and varying degrees of complexity.
Program summary:
1. Introduction to NLP.
2. Overview of NLP tasks. State-of-the-art and challenges.
3. Morphological analysis. Methods and tools.
4. Syntactic analysis (parsing).
4.1 Types of
representation: phrase structures vs. dependency structures.
4.2 Algorithms of
parsing: top-down, bottom-up, filter method.
5. Lexicons for NLP: types of lexical information and its
representation.
6. Machine translation.
7. Semantic representation: methods of representation and strategies.
8. Pragmatic interpretation. Modeling of context.
9. Applications.
Selected
bibliography:
Complementary information (course 2007-08)