Главная
Study mode:
on
1
– Welcome to class
2
– Machine translation
3
– Beam search
4
– How alignment works
5
– Translation with uncertainty
6
– Evaluation
7
– The long tail of languages
8
– Study case: Nepali ↔ English translation
9
– Low resource machine translation
10
– FLoRes evaluation benchmark and process
11
– ML perspective
12
– Supervised learning
13
– Self-supervised learning DAE
14
– Semi-supervised learning ST
15
– Semi-supervised learning BT
16
– Semi-supervised learning ST + BT
17
– Multi-task/-modal learning
18
– Domain adaptation
19
– Unsupervised MT
20
– FLoRes Ne-En
21
– Source target domain mismatch
22
– Final remarks
Description:
Explore the intricacies of low resource machine translation in this comprehensive lecture by Marc'Aurelio Ranzato. Delve into key concepts such as beam search, alignment techniques, and translation with uncertainty. Examine the challenges posed by the long tail of languages, focusing on a case study of Nepali-English translation. Learn about various machine learning approaches, including supervised, self-supervised, and semi-supervised learning methods. Discover the FLoRes evaluation benchmark and process, and gain insights into domain adaptation and unsupervised machine translation. Conclude with an analysis of source-target domain mismatch and final remarks on the future of low resource machine translation.

Low Resource Machine Translation

Alfredo Canziani
Add to list
0:00 / 0:00