# Logion: Machine Learning for Greek Philology

arXiv: https://arxiv.org/abs/2305.01099 · HTML: https://mlsanity.com/paper/2305.01099/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 1 May 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)
- [DEMix Layers: Disentangling Domains for Modular Language Modeling](https://mlsanity.com/paper/2108.05036/) (2021)
- [Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog](https://mlsanity.com/paper/1912.12800/) (2019)
- [Restoring ancient text using deep learning: a case study on Greek epigraphy](https://mlsanity.com/paper/1910.06262/) (2019)
- [Attention Can Reflect Syntactic Structure (If You Let It)](https://mlsanity.com/paper/2101.10927/) (2021)

## Built on by (most cited first, 3 of 3)

- [Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation](https://mlsanity.com/paper/2308.13116/) (2023)
- [Mind the Gap: Analyzing Lacunae with Transformer-Based Transcription](https://mlsanity.com/paper/2407.00250/) (2024)
- [The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions](https://mlsanity.com/paper/2603.09470/) (2026)

## Abstract (arXiv)

This paper presents machine-learning methods to address various problems in Greek philology. After training a BERT model on the largest premodern Greek dataset used for this purpose to date, we identify and correct previously undetected errors made by scribes in the process of textual transmission, in what is, to our knowledge, the first successful identification of such errors via machine learning. Additionally, we demonstrate the model's capacity to fill gaps caused by material deterioration of premodern manuscripts and compare the model's performance to that of a domain expert. We find that best performance is achieved when the domain expert is provided with model suggestions for inspiration. With such human-computer collaborations in mind, we explore the model's interpretability and find that certain attention heads appear to encode select grammatical features of premodern Greek.