Tag
This paper analyzes 122 languages to show that dependency length minimization operates differently for functional dependencies (short and invariant) versus lexical dependencies (longer and variable), suggesting that grammar provides local scaffolding for processing.
This paper introduces UD_Czech-PDTC, a large and genre-diverse treebank for Czech in the Universal Dependencies framework, derived from the Prague Dependency Treebank-Consolidated. It describes the conversion process and differences between annotation schemes.
Large language models can improve translation for low-resource languages through structured linguistic reasoning traces, with the most significant benefits occurring during inference rather than training.
This paper investigates whether large language models encode syntactic abstractions like phase boundaries that are not captured by Universal Dependencies, using structural probes on wh-movement stimuli with invariant UD distances, finding evidence across 13 LLMs for phase-structure representations that are causally active.
This paper presents a reproducible pipeline for building Universal Dependencies-style parsing resources for Katharevousa Greek parliamentary text, including OCR reconstruction, LLM-assisted annotation, and evaluation of multiple parsers. The best model (XLM-R) achieves 0.8893 UPOS accuracy and 0.5162 LAS, significantly outperforming off-the-shelf baselines.
CAIT is an open-source toolkit for syntactic parsing of child-adult interactions, featuring a dependency parser, POS tagger, and construction tagger trained on the UD-English-CHILDES treebank, outperforming general English parsers like SpaCy and Stanza.
Georgetown researchers boost low-resource Coptic-to-English translation by augmenting in-context prompts with Universal Dependencies syntactic parses alongside bilingual glosses, setting a new state-of-the-art.