On GATE, Text and Social Media Analysis, and Detecting Misinformation Online

2026-07-02 · Source: On GATE, Text and Social Media Analysis, and Detecting Misinformation Online · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Advanced, quick

Summary

Roberto A. Díaz Hernández, a Junior Lecturer at the University of Jaén, is developing Ancient Language Processing tools for Egyptian, specifically the Universal Dependencies Egyptian_Pre-Coptic Treebank (EPC treebank). This project annotates morphological features and syntactic relations across Old, Middle, Classical, Late Egyptian, and Demotic texts. The EPC treebank's latest release (v2.18 in Mai 2026) contains 34,234 tokens and 3,089 sentences from the Pyramid Texts, dating from approximately 2543–2120 BC. During a nine-week ATRIUM research visit to the University of Sheffield from April 20 to June 30, 2026, Díaz Hernández annotated over 5,000 additional tokens for the EPC treebank. He also developed and publicly released the EPC parser, a morphosyntactic model trained using the EPC treebank, and engaged with research teams to further its development.

Key takeaway

For NLP Engineers or Research Scientists working with low-resource or historical languages, this project demonstrates a viable path for creating essential linguistic tools. You should explore the publicly available EPC parser and the Universal Dependencies Egyptian_Pre-Coptic Treebank as a model for developing similar resources. Consider how collaborative research visits and open-sourcing your tools can accelerate progress and broaden impact in specialized linguistic domains.

Key insights

A publicly available morphosyntactic parser and treebank for Ancient Egyptian were created, advancing ancient language processing.

Principles

• Digital humanities benefit from NLP.
• Collaborative research accelerates development.
• Publicly available tools foster wider adoption.

Method

The method involved annotating morphological features and syntactic relations of ancient texts to build a Universal Dependencies treebank, then training a morphosyntactic parser on this data.

In practice

• Access the EPC parser online.
• Utilize the EPC treebank for research.
• Contribute to ancient language NLP.

Topics

• Ancient Language Processing
• Universal Dependencies
• EPC Treebank
• Morphosyntactic Parsing
• Digital Humanities
• Ancient Egyptian

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation — Syntactic augmentation via Universal Dependencies significantly improves low-resource Coptic-to-English machine translation when combined with dictionary glosses.
• A elaboração de uma edição digital d’Os Lusíadas — Integrating philology, Digital Humanities, and NLP creates comprehensive digital critical editions.
• Curation of a Palaeohispanic Dataset for Machine Learning — A new structured dataset enables machine learning analysis of under-resourced Palaeohispanic languages.
• Parsing Nheengatu: Performance Gains for a Brazilian Indigenous Universal Dependencies Treebank — Corpus expansion and standardized annotation improve parsing accuracy and reduce variance for low-resource languages.
• AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages — AfriSUD provides the first large-scale, native-speaker verified dependency treebanks for nine diverse African languages, revealing a significant syntax gap in current NLP models.
• A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts — A new dataset, SCAM, highlights significant challenges for Handwritten Text Recognition in low-resource historical scripts like Sahidic Coptic.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by On GATE, Text and Social Media Analysis, and Detecting Misinformation Online.