{"slug": "a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text", "title": "A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text", "summary": "Researchers have developed a reproducible NLP pipeline for Katharevousa Greek, a historical language variant used in Greek parliamentary archives, by creating a Universal Dependencies-style parsing resource from 1,697 sentences of post-junta parliamentary questions. The pipeline, which includes OCR reconstruction and LLM-assisted annotation, achieved a best LAS of 0.5162 using an XLM-R model, significantly outperforming off-the-shelf parsers like spaCy Greek. The entire workflow, code, and annotated dataset are publicly released to enable auditable syntactic analysis of historical parliamentary texts.", "body_md": "arXiv:2605.22978v1 Announce Type: new\nAbstract: Katharevousa Greek remains poorly served by contemporary NLP pipelines despite its importance for legal, administrative, and parliamentary archives. We present a reproducible workflow for building and evaluating a Universal Dependencies-style parsing resource for Katharevousa parliamentary questions from Greece's early post-junta period. The pipeline links OCR-aware reconstruction, schema-constrained LLM-assisted annotation, automatic validation, deterministic CoNLL-U snapshotting, fixed-split evaluation, and model-family comparison. The frozen automatically validated reference set contains 1{,}697 sentences, split into 1{,}357 training sentences and 340 held-out test sentences. We compare off-the-shelf Greek and Ancient Greek parsers, a feature-based parser, mBERT, XLM-R, and custom Stanza training under the same scoring protocol. Off-the-shelf systems show substantial register mismatch: the strongest external baseline, spaCy Greek, reaches 0.4183 LAS. The best structural parser, an XLM-R model, reaches 0.8893 UPOS accuracy, 0.7250 dependency-relation F1, 0.6098 UAS, and 0.5162 LAS, an absolute LAS gain of 0.0980 over the best external baseline. The feature-based model remains competitive for UPOS and relation labeling, indicating that transparent lexical-context features still matter at this data scale. Beyond scores, the paper contributes an auditable methodology for turning difficult historical parliamentary OCR into reusable syntactic NLP infrastructure. The entire pipeline -- code, schema, frozen reference annotations, fixed train/test split, and per-model benchmark reports -- is released as an open-access companion to this paper.", "url": "https://wpnews.pro/news/a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text", "canonical_source": "https://arxiv.org/abs/2605.22978", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:26:00.538330+00:00", "lang": "en", "topics": ["natural-language-processing", "machine-learning", "large-language-models", "neural-networks", "ai-research"], "entities": ["Universal Dependencies", "spaCy", "mBERT", "XLM-R", "Stanza", "Katharevousa Greek", "Greece", "OCR"], "alternates": {"html": "https://wpnews.pro/news/a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text", "markdown": "https://wpnews.pro/news/a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text.md", "text": "https://wpnews.pro/news/a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text.txt", "jsonld": "https://wpnews.pro/news/a-reproducible-universal-dependencies-style-pipeline-for-katharevousa-greek-text.jsonld"}}