Martijn Naaijer

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)

Papers

1. Identifying Phrase Boundaries in the Samaritan Pentateuch with Machine Learning (2026)
   The full text is not in the library (the publisher's page refused access); this card rests on the abstract as indexed by OpenAlex, and its ideas are provisional.
2. Towards an Integrated Methodology of Dating Biblical Texts: The Case of the Book of Jeremiah (2025)
   This is a project overview, not a result paper. The authors want to date the language of the Book of Jeremiah by combining redaction criticism, which splits the book into sources and layers, with linguistic dating of Biblical Hebrew, in which Classical (CBH) and Late (LBH) features are counted. They review the…
3. 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.
4. Clause Structure Variation in Biblical Hebrew: A Quantitative Approach (2020)
   The full text is not in our library, and the repository page gives no abstract text, so this card rests on the title, the catalogue record (249 pages; keywords Biblical Hebrew, syntax, machine learning, statistics).
5. Parallel Texts in the Hebrew Bible, New Methods and Visualizations (2016)
   An open method for finding parallel passages inside the Masoretic Text (ETCBC data, SHEBANQ). The Bible is cut into chunks (fixed word windows, or sentences, half-verses, verses, chapters); every pair is scored either by SET similarity (Jaccard overlap of lexeme sets, ignoring order) or by LCS/Levenshtein similarity…
6. Syntactic Variation in Masoretic Hebrew: The Object Clause Reconsidered (2016)
   The full text is not in the library; this card rests on the publisher's abstract, so the ideas are provisional.
7. An Alternative Approach to the Lexicon of Late Biblical Hebrew (2016)
   A variationist answer to Hurvitz's Concise Lexicon of Late Biblical Hebrew (2014), which lists 80 late words with their early equivalents (e.g.
8. LAF-Fabric: a data analysis tool for Linguistic Annotation Framework with an application to the Hebrew Bible (2014)
   The paper traces the ETCBC (formerly WIVU) Hebrew Bible database from the 1970s to its conversion into ISO LAF stand-off annotation (the SHEBANQ project), and presents LAF-Fabric, a Python tool that loads the whole annotated Bible into memory for fast feature queries (a precursor of Text-Fabric).

Co-authors (12)

• Dirk Roorda ×3
• Andreas van Cranenburgh
• Aren Wilson-Wright
• Christian Canu Højgaard
• Constantijn Sikkel
• Gino Kalkman
• Jisk Attema
• Mathias Coeckelbergs
• Oliver Glanz
• Robert Rezetko
• Saulo de Oliveira Cantanhede
• Willem Th. Van Peursen

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/martijn-naaijer/