# 'UFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin

arXiv: https://arxiv.org/abs/2404.05839 · HTML: https://mlsanity.com/paper/2404.05839/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP](https://mlsanity.com/paper/2005.14672/) (2020)
- [Latin BERT: A Contextual Language Model for Classical Philology](https://mlsanity.com/paper/2009.10053/) (2020)
- [Exploring Large Language Models for Classical Philology](https://mlsanity.com/paper/2305.13698/) (2023)
- [UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings](https://mlsanity.com/paper/2006.03687/) (2020)

## Built on by (most cited first, 2 of 2)

- [CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17858/) (2025)
- [It takes a village to write a book: Mapping anonymous contributions in Stephen Langton's Quaestiones Theologiae](https://mlsanity.com/paper/2508.12830/) (2025)

## Abstract (arXiv)

We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe.