NTNU logo

TDT13 - Advanced Text Analytics and Language Understanding

(Avansert tekstanalyse og språkforståelse, 2020)

Teoritema

IDI > Education > Emner > TDT13 Advanced Text Analytics and Language Understanding

(Avansert tekstanalyse og språkforståelse, 2020)

Advanced Text Analytics and Language Understanding

(Avansert tekstanalyse og språkforståelse, 2020)

Given by Björn Gambäck.

The course consists of a set of regular lectures and student presentations, as well as a short exam (written or oral).

Note that the course content in general is tailored towards the needs of the students writing a Master's Thesis in Language Technology and/or have taken the course TDT4310 (Intelligent Text Analytics and Language Understanding/Intelligent tekstanalyse og språkforståelse), or something similar (e.g., during an exchange visit abroad).
Other students are of course very welcome to follow the course, but are adviced to contact the lecturer beforehand.
(However, a short introduction to/overview of language technology will be included at the beginning of the course.)

This year we will in particular discuss:

  • semantic representations and processing,
  • word embeddings and word-space modelling,
  • transfer learning, transformers and self-attention,
  • language evolution and simulation,
  • and in general classification algorithms for language processing, applied to issues such as:
    • sentiment analysis
    • author profiling
    • hate speech identification
  • NB: the name of course has changed (from the previous "Computational Semantics") in order to reflect changes in the course themes.

    Course Material

    The course material (lecture recordings and slides, articles, etc.) will be published in the course Teams group.

    Prel. Course Schedule

    The course will start on Tuesday 15.9 at 14:15-16:00 in room 454.

    Given the corona situation, most lectures will be given online only. However, those who want can (also) physically attend the first lecture: Room 454 (IT-bygget, 4th floor) is the IDI department's largest meeting room, so social distancing should be no problem.

    1. Tuesday September 15, 14:15-16:00, room 454: Introduction
    2. Tuesday September 29, 14:15-16:00, Teams: Machine Learning and Deep Learning for NLP
    3. Tuesday October 13, 14:15-16:00, Teams: Text Analysis; Sentiment Analysis
    4. Tuesday October 27, 14:15-16:00, Teams: Language Classification Applications:
      1. Author Profiling
      2. Hate Speech Detection
      3. Native Language Identification

    5. Thursday November 19: Presentations
    6. November 26-27 (probably): Oral Exam

     


    Visiting hour

    by appointment

     


    For nærmere informasjon om emnet, kontakt faglærer Björn Gambäck.