Telecom ParisTech
Dep. Informatique & Réseaux

J-L. Dessalles Home page

April 2019



Symbolic Natural Language Processing (SD213)

                                other AI courses

→        Goto the course Website.

Objectives

Processing language is one of the most important and most challenging issues of Artificial Intelligence. NLP (Natural Language Processing) has many applications. It is commonly used in machine translation, in text proofing, in speech recognition, in dialogue based applications, in optical character recognition, in text mining, in spam filtering, in text generation, in automatic summarization, in speech synthesis, in computer assisted learning, in database indexing and Web search, etc. Conversely, it is hard to imagine an "intelligent" machine that would be unable to understand language.

NLP comes in two flavours. Many current approaches to language processing are based on large collections of texts. Statistics and machine learning provide quite good predictions about syntax, meaning and intentions. By contrast, symbolic approaches to NLP give priority to the analysis of structures and to exact computation. Often inspired by cognitive analyses, symbolic NLP takes the word "processing" literally: the ultimate goal is to reproduce computations that human individuals are supposed to perform when talking relevantly.

Content

This course is about symbolic NLP. The techniques and concepts that will be studied have however a broader scope in artificial intelligence and are used to study reasoning, decision making and symbolic machine learning. They include:

Prerequisites

Students are supposed to have followed SD206 (Logic and knowledge representation), or equivalent.

Teaching

The course will alternate lectures and lab work sessions.

Evaluation