Computational analysis of medieval manuscripts: a new tool for analysis and mapping of medieval documents to modern orthography
Bibliographic record
Abstract
Medieval manuscripts or other written documents from that period contain \nvaluable information about people, religion, and politics of the medieval period, making \nthe study of medieval documents a necessary pre-requisite to gaining in-depth knowledge \nof medieval history. Although tool-less study of such documents is possible and has \nbeen ongoing for centuries, much subtle information remains locked such manuscripts \nunless it gets revealed by effective means of computational analysis. Automatic analysis \nof medieval manuscripts is a non-trivial task mainly due to non-conforming styles, \nspelling peculiarities, or lack of relational structures (hyper-links), which could be used \nto answer meaningful queries. Natural Language Processing (NLP) tools and algorithms \nare used to carry out computational analysis of text data. However due to high \npercentage of spelling variations in medieval manuscripts, NLP tools and algorithms \ncannot be applied directly for computational analysis. If the spelling variations are \nmapped to standard dictionary words, then application of standard NLP tools and algorithms \nbecomes possible. In this paper we describe a web-based software tool CAMM \n(Computational Analysis of Medieval Manuscripts) that maps medieval spelling variations \nto a modern German dictionary. Here we describe the steps taken to acquire, \nreformat, and analyze data, produce putative mappings as well as the steps taken to \nevaluate the findings. At the time of the writing of this paper, CAMM provides access \nto 11275 manuscripts organized into 54 collections containing a total of 242446 \ndistinctly spelled words. CAMM accurately corrects spelling of 55% percent of the verifiable \nwords.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.008 | 0.008 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.009 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.013 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".