v2.11.0 (5747)

Enseignement scientifique & technique - SD213 : Cognitive approach to Natural Language Processing (Option Gestion des données)

Domaine > Informatique.

Descriptif

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 mining, in speech recognition, in dialogue based applications, in text generation, in automatic summarization, in Web search, etc. Conversely, it is hard to imagine an “intelligent” machine that would be unable to understand language.

NLP remains a challenging task. Statistical techniques perform well in domains such as machine translation, but they are intrinsically limited to average meanings and cannot take contextual knowledge into account. This course explores some symbolic alternatives to mere statistics.

Some NLP techniques, like grammar and parsing and ontologies, are classic symbolic methods. Some others are inspired by cognitive modelling. They include procedural semantics, aspect processing, dialogue processing. The point is not only to adopt a “reverse engineering” approach to language, but also to adapt engineering techniques to human requirements to improve efficiency and acceptability.

Objectifs pédagogiques

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 mining, in speech recognition, in dialogue based applications, in text generation, in automatic summarization, in Web search, etc. Conversely, it is hard to imagine an “intelligent” machine that would be unable to understand language.

NLP remains a challenging task. Statistical techniques perform well in domains such as machine translation, but they are intrinsically limited to average meanings and cannot take contextual knowledge into account. This course explores some symbolic alternatives to mere statistics.

Some NLP techniques, like grammar and parsing and ontologies, are classic symbolic methods. Some others are inspired by cognitive modelling. They include procedural semantics, aspect processing, dialogue processing. The point is not only to adopt a “reverse engineering” approach to language, but also to adapt engineering techniques to human requirements to improve efficiency and acceptability.

Format des notes

Numérique sur 20

Littérale/grade européen

Pour les étudiants du diplôme Data & Artificial Intelligence

L'UE est acquise si Note finale >= 10
  • Crédits ECTS acquis : 2.5 ECTS

La note obtenue rentre dans le calcul de votre GPA.

Pour les étudiants du diplôme Programme de mobilité des établissements français partenaires

L'UE est acquise si Note finale >= 10
  • Crédits ECTS acquis : 2.5 ECTS

Pour les étudiants du diplôme Diplôme d'ingénieur

Vos modalités d'acquisition :

  • Answers to questions during lab sessions will be recorded. They will be evaluated when students who are close to failing based on other criteria.
  • Students will be asked to perform a small technical study by extending some issue addressed during lab sessions. They will be given the opportunity to present their work during a few minutes at the end of the course. They will also write a four-page report.
  • Students will answer a small quiz (open questions, no documents).

L'UE est acquise si Note finale >= 10
  • Crédits ECTS acquis : 2.5 ECTS
  • Crédit d'UE électives acquis : 2.5

La note obtenue rentre dans le calcul de votre GPA.

Pour les étudiants du diplôme Interaction, Graphic & Design

L'UE est acquise si Note finale >= 10
  • Crédits ECTS acquis : 2.5 ECTS

Pour les étudiants du diplôme Echange international non diplomant

L'UE est acquise si Note finale >= 10
  • Crédits ECTS acquis : 2.5 ECTS

La note obtenue rentre dans le calcul de votre GPA.

Méthodes pédagogiques

The course will alternate lectures and lab work sessions.
Veuillez patienter