Version 4.2

Workshop: Basics of NLP: Language Modeling

Language models attempt to measure the likelihood of a sequence of words occurring in an utterance of a given language. They are a cornerstone of several classical natural language processing (NLP) tasks including automatic speech recognition and machine translation and the parameter estimation techniques often used for developing a language model can also be found in numerous other basic and more advanced tasks. For this reason, language models lend themselves as a good subject for a first taste of NLP methods.

In this workshop, you will get acquainted with the basic theory behind n-gram language models and you will also get a glimpse of more recent techniques out there. Crucially, the workshop includes several exercises for applying the theory in order to make this an actual workshop and not an overly long presentation. The exercises aim to be of various degrees of difficulty so that most everyone can profit from them. Some of them will be solvable using just pen and paper, others will make use of the Python programming language. If you want to take part in the Python exercises, be sure to install Python on your device beforehand.

If you have no programming experience and/or have never used Python before, this can be a nice way to start. If you have the time, try to familiarize yourself with the environment to the point where you can write and run a simple program that prints something to the screen.
https://www.python.org/about/gettingstarted/

This workshop will take place in a computer pool room. Please note that the computers are only accessible to members of the University of Cologne. Other participants need to bring their own devices.

Info

Tag: 23.05.2019
Anfangszeit: 14:00
Dauer: 01:30
Raum: 103 / CIP-Pool 72
Track: Computational Linguistics
Sprache: en

Links:

Feedback

Uns interessiert Ihre Meinung! Wie fanden Sie diese Veranstaltung?

Gleichzeitige Events