Pre-trained encoder-decoder transformers fine-tuned for sequence-to-sequence constituent parsing outperform prior seq2seq models and compete with specialized parsers on continuous treebanks.
Hidden technical debt in machine learning systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Empirical study of Stack Overflow posts on ML libraries finds prevalent API misuses, lack of early error detection, and a need for more SE research on debugging and model behavior understanding.
citing papers explorer
-
Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing
Pre-trained encoder-decoder transformers fine-tuned for sequence-to-sequence constituent parsing outperform prior seq2seq models and compete with specialized parsers on continuous treebanks.
-
What Do Developers Ask About ML Libraries? A Large-scale Study Using Stack Overflow
Empirical study of Stack Overflow posts on ML libraries finds prevalent API misuses, lack of early error detection, and a need for more SE research on debugging and model behavior understanding.