Machine Translation (PV061)
Pavel Rychlý
Optional Assigments
Optional Assigments
You can earn extra points for the exam.
Errors in translations
(2-3 point for a group)
find erros in machine translaton
choose any system (Google, DeepL, . . . )
translate a document
report and describe errors
try to find shortest sentence containing that error
Errors in traning data
(2-3 point for a group)
look at some training data for translation
find errors
wrong alignments
wrong language
non-fluent sentences
Compare small optimizations
(10 points)
find a NMT system
train with original setup
train with a small optimizaton
different tokenizer (BPE/SentencePiece)
shared/separate embeddings
compare results
Replicate SotA results on own data
find a NMT implementation
run on own data (Cz-En ficet)
compare results