Natuurlijke Taalmodellen en Interfaces

Natural Language Models and Interfaces

Studiewijzer 2019/2020

Globale inhoud

Natural language is the main channel of communication between humans, and much of human knowledge is represented
in the form of natural language. Enabling computers to understand it is an extremely important task, and is one of the
core problems of artificial intelligence. Though full understanding still remains a remote goal, robust methods have been
developed for more shallow forms of processing, and these methods and corresponding formalisms are the focus of this
course.

In this course you learn about formalisms and techniques to assign probabilities to (parts of) sentences (language
modeling) and to perform basic forms of syntactic and semantic processing.  These techniques are the foundation of current data-driven computational linguistics and provide building blocks for speech recognition,
language understanding, text summarisation, and machine translation systems.

Studiemateriaal

Literatuur

• Daniel Jurafsky & James H. Martin, 'Speech and Language Processing' (3rd Edition) Pearson Prentice Hall, 2019.

Leerdoelen

• The student is able to design statistical models to analyse and predict correlations in natural language data.
• The student is able to apply statistical modelling to predict linguistic generalisations such as syntactic, semantic, and morphological structure.
• The student can describe the computational challenges of this statistical approach
• The student can use data structures and algorithms to deploying NLP models, implementing statistical estimators, and using NLP libraries.

Onderwijsvormen

• Hoorcollege
• Werkcollege
• (Computer)practicum

The class will consist of a theoretical course and practical sessions. Practical sessions involve coding assignments using jupyter notebooks. 

Verdeling leeractiviteiten

Aanwezigheid

Aanwezigheidseisen opleiding (OER-B):

• Voor practica en werkgroepbijeenkomsten met opdrachten geldt een aanwezigheidsplicht. De invulling van deze aanwezigheidsplicht kan per vak verschillen en staat aangegeven in de studiewijzer. Wanneer studenten niet voldoen aan deze aanwezigheidsplicht kan het onderdeel niet met een voldoende worden afgerond.
  

Toetsing

The grade will be 40% homework (weighted average of 5 assignments) and 60% exams (weighted average of midterm and final). Both components (exam and homework) are initially graded on a scale from 0 to 10 and they must each be at least 5.0 in order to pass the course (see Dutch scaling below). If your exam component is below 5.0 you are eligible to a resit which fully replaces that component. 

Dutch scaling

According to official UvA regulations your final grade has to be between 1 and 10. To avoid confusion, this is how we compute your final grade: 1 + 0.9 * (0.6 * exams + 0.4 * homework). This grade is rounded to the closest half point, or to the closest point if it falls between 5 and 6. 

Inzage toetsing

Om een inzagemoment aan te vragen, kun je contact opnemen met de coördinator.

Opdrachten

• Assessed practical assignments: students work in pairs. Feedback is provided by TA through canvas and/or in person.
• Non-assessed quizzes and reading questions available on canvas.
• Non-assessed exam-like exercises.

Fraude en plagiaat

Dit vak hanteert de algemene 'Fraude- en plagiaatregeling' van de UvA. Hier wordt nauwkeurig op gecontroleerd. Bij verdenking van fraude of plagiaat wordt de examencommissie van de opleiding ingeschakeld. Zie de Fraude- en plagiaatregeling van de UvA: http://student.uva.nl

Weekplanning

Rooster

Het rooster van dit vak is in te zien op DataNose.

Aanvullende informatie

The course will be taught in English.

Prerequisite skills: Basic probability theory, programming in python. 

Verwerking vakevaluaties

1. We are keeping the midterm
2. We have reduced the amount of homework around the final exam

Contactinformatie

Coördinator

• W. Ferreira Aziz