BERTGraph, which adds rule-extracted relational graphs to BERT via a graph convolutional network, improves news classification accuracy over fine-tuned BERT on N24News and Snopes datasets.
Revisiting the Effects of Leakage on Dependency Parsing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recent work by S{\o}gaard (2020) showed that, treebank size aside, overlap between training and test graphs (termed leakage) explains more of the observed variation in dependency parsing performance than other explanations. In this work we revisit this claim, testing it on more models and languages. We find that it only holds for zero-shot cross-lingual settings. We then propose a more fine-grained measure of such leakage which, unlike the original measure, not only explains but also correlates with observed performance variation. Code and data are available here: https://github.com/miriamwanner/reu-nlp-project
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge Bases in Support of Large Language Models for Processing Web News
BERTGraph, which adds rule-extracted relational graphs to BERT via a graph convolutional network, improves news classification accuracy over fine-tuned BERT on N24News and Snopes datasets.