Tweeted By @ml_review

on 2018-08-31 (UTC)
nlp survey

a group with 1 other tweets.

Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures
w/ @RicoSennrich

1) self-attentional & CNNs do not outperform RNNs in subject-verb agreement
2) self-attentional outperform RNNs & CNNs on word sense disambiguationhttps://t.co/TIvuYMUuLe pic.twitter.com/Og01mkqs5K
— ML Review (@ml_review) August 31, 2018

Tags