GiLT augments Transformers with semantic dependency graphs by modulating attention to improve syntactic generalization while keeping perplexity competitive and enabling better finetuning on downstream tasks.
Unsupervised Recurrent Neural Network Grammars
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GiLT: Augmenting Transformer Language Models with Dependency Graphs
GiLT augments Transformers with semantic dependency graphs by modulating attention to improve syntactic generalization while keeping perplexity competitive and enabling better finetuning on downstream tasks.