# Correction as Annotation: Bootstrapping a Dependency Parser for Documentary Medieval Latin

arXiv: https://arxiv.org/abs/2609.06266 · HTML: https://mlsanity.com/paper/2609.06266/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 103 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Statistically Significant Detection of Linguistic Change](https://mlsanity.com/paper/1411.3315/) (2014)
- [A Large-Scale Comparison of Historical Text Normalization Systems](https://mlsanity.com/paper/1904.02036/) (2019)
- [Overcoming Language Variation in Sentiment Analysis with Social Attention](https://mlsanity.com/paper/1511.06052/) (2015)
- [Challenges of Computational Processing of Code-Switching](https://mlsanity.com/paper/1610.02213/) (2016)

## Abstract (arXiv)

Medieval documentary sources remain inadequately served by existing natural language processing tools. None of the five readily available Latin treebank models attains usable performance on a collection of 160 inventories compiled in Marseille between 1258 and 1446. The best labelled attachment score is 0.62 and the best morphology-aware score is 0.24. Performance does not correlate with either genre or period proximity. To address this shortfall, in-domain training data was generated as a by-product of using these inadequate models. In each of nine iterations, a model pre-annotated 200 sentences; an expert corrected the annotations; and the corrected sentences were used to train the subsequent model, with batches sampled independently of model state, without active-learning selection. Thirty-three hours of annotation effort over 1,804 sentences increased universal part-of-speech accuracy from 0.80 to 0.98 and labelled attachment from 0.48 to 0.92, outperforming all baselines on the reported metrics while using 97% less training data than the largest one of them. Annotator effort declined from 54% of tokens to a plateau of 14-18%, an operational progress metric that requires no separate gold standard and can serve as a stopping criterion.