Mathias Coeckelbergs

2 paper cards in Mova's library · 2022–2023

Mathias Coeckelbergs wrote 2 of the papers Mova reads, in 2022–2023; often with Constantijn Sikkel, Jisk Attema, Martijn Naaijer.

The profile is the library's match of the name; two people with one name are not always told apart.

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

kept — Consonant check: the first error category (the predicted consonantal form differs from the surface text) needs no linguistics. (A Transformer-based parser for Syriac morphology · consonant check in tools/hbo (Model::spells, no-check as negative control): 0 failures on dev, test and cv (278 799 tokens); commit 5c24bc409)

A Transformer-based parser for Syriac morphology (2023) 1 idea kept
The authors train a Transformer sequence-to-sequence model from scratch to produce ETCBC-style morphological analyses of Syriac text, one verse per line, with each graphical unit split into words and morphemes.
From Pattern to Interpretation. Using Colibri Core to Detect Translation Patterns in the Peshitta. (2022)
This is a progress report of a project that uses Colibri Core, a language-independent n-gram, skipgram and flexgram counter, to compare the Hebrew Bible with its Syriac translation, the Peshitta.