This paper presents a corpus-based analysis of argument structure errors...
Pre-trained seq2seq models excel at graph semantic parsing with rich
ann...
Accurate uncertainty quantification is a major challenge in deep learnin...
Content moderation is often performed by a collaboration between humans ...
Knowledge distillation is one of the most popular and effective techniqu...
Traditional (unstructured) pruning methods for a Transformer model focus...
Bayesian neural networks (BNN) and deep ensembles are principled approac...
Autoregressive sequence models achieve state-of-the-art performance in
d...
Due to the unparallelizable nature of the autoregressive factorization,
...
We present a phenomenon-oriented comparative analysis of the two dominan...
Previously, researchers paid no attention to the creation of unambiguous...
This paper studies semantic parsing for interlanguage (L2), taking seman...