Semester: Spring 2018
When and where: from 1st March till 1st June 2018 on the following days:
  • Thursday (16.30-18.30), aula 2 - Aule L ingegneria, via del Castro Laurenziano
  • Friday (14.00-16.00), aula 2 - Aule L ingegneria, via del Castro Laurenziano

Contact information

Instructor: Prof. Roberto Navigli
Office: room G24, viale Regina Elena, 295 (pal. G)
Phone number: 06 49255161
Email: surname chiocciola di plus uniroma1 plus it (if you are a human being, please replace plus with . and chiocciola with @)
Tutors: Valentina Pyatkin and Federico Scozzafava

Basic information

The Natural Language Processing course introduces a field of Artificial Intelligence which deals with the automatic processing of natural language. The course is taught in English. The student will understand the theoretical and practical fundamentals of how to process natural language automatically at the different levels of morphology, part-of-speech tagging, syntax, semantics, discourse and dialogue. Machine translation and other applications will also be introduced.

The course is currently in the curriculum of both the Laurea Magistrale in Informatica, Master Degree in AI and Robotics and the Laurea Magistrale in Ingegneria Informatica.



Note that this is new as of 2018:
  • Attending students: three homeworks, one of which to be delivered by the end of September 2018.
  • Non-attending students: a full-fledged project. Project delivery can be done at any time (between 1st June and 30th September 2018 and 1st  January and 22nd February 2019) by sending the project to the tutors.
The student has to deliver 1) the source code, 2) any additional data needed to run the software, 3) a 4-page paper (+infinite pages for references) including: a brief introduction to the project problem, a brief state-of-the-art, an illustration of the methods/approach/techniques (min. 1 page), a quantitative (and ideally a small qualitative) evaluation of the system.

The project will be presented orally. Assessment is done every 20-30 days, with discussion meetings by appointment. 
Course outline

  • Introduction to Natural Language Processing
  • Computational morphology
  • N-gram language models; smoothing; interpolation; backoff
  • Part-of-speech tagging  (including multilingual POS tagging)
  • Syntactic parsing: CYK algorithm; Earley's algorithm; statistical and neural techniques.
  • Computational semantics and lexical semantics
  • Computational lexicons: WordNet
  • Multilingual semantic networks: BabelNet
  • Word Sense Disambiguation and Induction; Entity Linking
  • Neural networks, word embeddings and deep learning
  • Semantic parsing
  • Statistical and Neural Machine Translation

No comments:

Post a Comment