Papers with online knowledge distillation

2 papers
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task (2021.acl-long)

Copied to clipboard

Challenge: Pretraining and multitask learning are widely used to improve the speech translation performance.
Approach: They propose to train a speech translation model along with an auxiliary text translation task.
Outcome: The proposed method improves translation quality by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the MuST-C English-German, English-French and English-Spanish language pairs.
Norm-based Noisy Corpora Filtering and Refurbishing in Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing noisy corpora filtering methods are insufficient to solve this problem, requiring multiple scorers trained on clean bitexts.
Approach: They propose to use the information ratio from the source to the target side to distinguish unparallel sentence pairs by using norms of context vectors.
Outcome: The proposed method performs comparably with state-of-the-art noisy corpora filtering techniques but is more efficient and easier to operate.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations