Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Jason Y. Zhao"'
Autor:
Rajiv Movva, Jason Y. Zhao
Publikováno v:
BlackboxNLP@EMNLP
Recent work on the lottery ticket hypothesis has produced highly sparse Transformers for NMT while maintaining BLEU. However, it is unclear how such pruning techniques affect a model's learned representations. By probing Transformers with more and mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e8c7076f2dd3464beeb7ea89836d422
https://doi.org/10.18653/v1/2020.blackboxnlp-1.19
https://doi.org/10.18653/v1/2020.blackboxnlp-1.19
