Yhteystiedot

Yleisen kielitieteen laitos
PL 9 (Siltavuorenpenger 20 A)
00014 Helsingin yliopisto

Puhelinvaihde +358 (09) 1911
Faksi +358 (09) 191 29307

Kurssikuvaus

Esitiedot:

• Basic knowledge of general linguistics and language technology (for example clt110 and clt140)
• Basic knowledge of syntactic ideas and terms (for example clt125)
• Basic understanding of programs and programming (for example clt230)
• Previous experience of Python (for example clt230) will be helpful

Tavoitteet:

• The course introduces NLP tools and techniques for syntactic analysis.
• Students gain a basic theoretical understanding of the underlying concepts and techniques used in automatic syntactic analysis.
• Students gain hands-on experience of some of the practical problems, using the NLTK Natural Language ToolKit to do exercises and assignments.

Kurssin sisältö:

• Introduction: NLP tools, NLP programming
• Words: types and tokens
• Parts of speech: tagging, tagged corpora
• Sentences: syntax trees, constituency
• Grammars: CFGs, feature-based grammars
• Syntactic parsing: structural ambiguity, charts
• Probabilistic parsing: PCFGs, treebanks

Kirjallisuus:

• The course uses web-based study materials, including the NLTK tutorials.
• Jurafsky & Martin Speech and Language Processing, Prentice-Hall, 2000

Kurssin laajuus opintopisteinä:

3 op.

Opetus

Opettaja:

Graham Wilcock. Kurssikieli englanti.

Suoritustapa:

The course consists of lectures, practical lab exercises, and a series of assignments. It can be passed just by doing the assignments.

Paikka ja aika:

to 13-16 S20A laitoksen unix-luokka, 2.11. - 14.12

Kurssimateriaali:

Kurssin verkkosivuilla, ks. sivupalkki.