PA154 - Technical Informations
Introduction
PA154 Jazykové modelování (1.1) Pavel Rychlý
pary@fi.muni.cz
March 2, 2021
Slides and recorded videos in IS
https://is.muni.cz/auth/el/fi/jaro2021/PA154/index.qwarp Final written exam (online) 50 points, 25 points for E optional individual projects up to 25 points
Individual projects
Language models—what are they good for?
presentation on a new research in language modeling small project as a part of bigger collaborative projects
► neural machine translation
► lexical acquisition
assigning scores to sequencies of words predicting words generating text
statistical machine translation automatic speech recognition optical character recognition
Predicting words
Do you speak ...
Would you be so ...
Statistical machine ...
Faculty of Informatics, Masaryk .
WWII has ended in ...
In the town where I was ...
Lord of the ...
Generating text
□escribes without et rots
PA154 Jazykové modelování (1.1)
6/8
MT + OCR
Language models - probability of a sentence
BblXOA B rOPOfl
LM is a probability distribution over all possible word sequences. What is the probability of utterance of s?
P(./vf(Catalonia President urges protests) P(_/vj(President Catalonia urges protests) p^/vj(urges Catalonia protests President)
Ideally, the probability should strongly correlate with fluency and intelligibility of a word sequence.