90155 - Natural Language Processing (1) (LM)

Learning outcomes

At the end of this course, the student acquires advanced notions about Natural Language Processing with particular attention at the statistical/algorithmic techniques. The methods and instruments from Natural Language Processing will be then applied at each level of linguistic analysis.

Course contents

• Part I: Foundations
  • Introduction
    • Natural Language Processing - Problems and perspectives
    • Introduction/Recall to/of probability calculus
      • N-grams and Language Models
    • Deep Neural Networks
      
    • The evaluation of NLP applications
  • Corpora
    • Corpora and their construction: representativeness
    • Concordances, collocations and measures of words association
    • Methods for Text Retrieval

• Part II: Natural Language Processing
  
  • Computational Phonetics
    • Speech samples: properties and acoustic measures
    • Analysis in the frequency domain, Spectrograms
    • Applications in the acoustic phonetic field.
    • Speech recognition with Deep Neural Networks
  • Computational Morphology
    • Morphological operations
    • Static lexica, Two-level morphology
  • Computational Syntax
    • Part-of-speech tagging
    • Grammars for natural language
    • Natural language Parsing
    • Supplementary worksheet: formal grammars for NL
      • Formal languages and Natural languages. Natural language complexity
      • Phrase structure grammars, Dependency Grammars
      • Treebanks
      • Modern formalisms for parsing natural languages
  • Computational Semantics
    • Lexical semantics: WordNet and FrameNet
    • Word Sense Disambiguation
    • Word-Space models
    • Logical approaches to sentence semantics

• Part III: Applications and Case studies:
  • Solving Downstream Tasks
    • Document classification
    • Sentiment Analysis
    • Named Entity Recognition
    • Semantic Textual Similarity
  • Prompting Pre-Trained Language Models

 

Students with SLD or temporary or permanent disabilities. It is suggested that they get in touch as soon as possible with the relevant University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en) and with the lecturer in order to seek together the most effective strategies for following the lessons and/or preparing for the examination.

Readings/Bibliography

Some chapters extracted from:

• Tamburini F. (2022). Neural Models for the Automatic Processing of Italian, Pàtron.
• D. Jurafsky and J.H. Martin (2008). Speech and Language Processing, Prentice Hall.
• A. Clark, C. Fox, S. Lappin (2010). The Handbook of Computational Linguistics and Natural Language Processing, Blackwell Handbooks in Linguistics.
• Mitkow R. (ed.) (2003). The Oxford Handbook of Computational Linguistics.
• Ritchie C. and Mellish C. (2000). Techniques in Natural Language Processing.

Slides, handouts and papers downloadable from the course web site.

The course contents for students not attending the lessons are the same. However, students not able to attend the lessons are strongly invited to contact the teacher to get some explanations and avoid any misunderstanding about the course contents and reading materials.

Teaching methods

Face-to-face classes and labs for 30 hours.

In consideration of the type of activity and the teaching methods adopted, the attendance of this training activity requires the prior participation of all students in the training modules 1 and 2 on safety in the study places, in e-learning mode.

Assessment methods

Students attending this course can choose between two different exam types:

• develop a project, previously approved by the teacher, write a report on it (at least 10 pages) and discuss it at the oral exam with some other very general questions on other course topics. A list of project proposals can be found here [http://corpora.ficlit.unibo.it/NLP/index.php?slab=projects] . Students are allowed to suggest other project topics to the teacher;
• a classical oral colloquium consisting of at least three questions (either general or very specific) on the course contents.

The oral colloquium is designed to evaluate the critical skills and methodological knowledge gained by the student.

Reaching a clear view of all the course topics as well as using a correct language terminology will be valued with maximum rankings. Mnemonic knowledge of the course topics or not completely appropriate terminology will be valued with intermediate rankings. Unknown topics or inappropriate terminology use will be valued, depending on the seriousness of the omissions, with minimal or insufficient rankings.

With regard to the project report, a critical analysis of the problem and the proposed solution(s) as well as a proper evaluation of the proposed solution(s) are required to get maximum rankings.The exam consists of an oral colloquium on the course contents designed to evaluate the critical skills and methodological knowledge gained by the student.

The date for the exam can be arranged by appointment contacting the teacher. The report must be sent to the teacher at least 7 days before the exam date.

It is compulsory to register for the exam using the online procedure.

Students with SLD or temporary or permanent disabilities. It is necessary to contact the relevant University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en) with ample time in advance: the office will propose some adjustments, which must in any case be submitted 15 days in advance to the lecturer, who will assess the appropriateness of these in relation to the teaching objectives.

Teaching tools

The course web site is the central point for any kind of information about the course. It contains the handouts and the readings discussed during the lessons as well as a rich software repository.

Links to further information

https://corpora.ficlit.unibo.it/NLP/

Office hours

See the website of Fabio Tamburini