Semantic constituency graphs outperform syntactic constituency and dependency structures from seven formalisms when added to a Transformer for language modeling.
Do Neural Language Models Show Preferences for Syntactic Formalisms?
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
Truncated embeddings from non-MRL models perform comparably to or better than MRL-trained models for most truncation levels, except heavy truncation of 80% or more.
citing papers explorer
-
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
Semantic constituency graphs outperform syntactic constituency and dependency structures from seven formalisms when added to a Transformer for language modeling.
-
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.