Linking Your *-ographies: Developing project-specific TEI Authority File Lookups for LEAF-Writer
Bibliographic record
Abstract
James Cummings, Newcastle University, https://orcid.org/0000-0002-6686-3728 Luciano Frizzera, University of Waterloo, https://orcid.org/0000-0001-7244-4178 Diane Jakacki, Bucknell University, https://orcid.org/0000-0002-7836-1223 Susan Brown, University of Guelph, https://orcid.org/0000-0002-0267-7344 Mihaela Ilovan, University of Alberta, https://orcid.org/0000-0002-0649-4465 Kelsey Rubin-Detlev, University of Southern California, https://orcid.org/0000-0002-0654-0273 LEAF-Writer is a popular, free, web-based, semantic editor for Text Encoding Initiative (TEI) and Linked Open Data (LOD) annotation. While LEAF-Writer is available in a standalone version that anyone can use (LEAF-Writer Commons), it is also a crucial component of the larger LEAF-VRE environment. LEAF-Writer Commons runs entirely in your browser and files are saved to your own GitHub repositories (or downloaded locally), with no data stored on LEAF servers. LEAF-Writer provides an easy text-first editing interface that encourages the encoder to focus on adding semantic markup, scholarly notes, and identifying named entities. You can choose to edit in the tags-off view, show tags, or edit the underlying TEI XML. LEAF-Writer includes schema-constrained context-sensitive tagging and validation using out-of-the-box popular TEI customizations, or use your own custom TEI project schemas (with your own CSS). One of LEAF-Writer’s most important features is its built-in support for named entity linking. This enables tagging names of people, places, organisations, or works and associating these (with both TEI markup and LOD) to recognised authorities (such as VIAF, Wikidata, DBPedia, Getty, Geonames, GND and LINCS). LEAF-Writer can also generate LOD Annotations from already tagged XML references. Recently, the LEAF team, in collaboration with the CatCor (Correspondence of Catherine the Great) project has introduced functionality for adding web-accessible project-specific TEI Authority files for particular entity types. (e.g. a TEI ‘personography’ file containing a for person entities, for place entities, etc.). This exciting new feature is for many TEI projects that want to do look-ups using their own project-specific ‘*-ography’ authority files. LEAF-Writer was introduced at TEI2022 and we have run workshops and presented new features to the TEI community in the years since. For this conference, we will concentrate on these ‘new territories’ of project-specific TEI Authority Files for named entity lookups.
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 | 0.007 | 0.035 |
| Meta-epidemiology (narrow) | 0.003 | 0.003 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.007 | 0.013 |
| Open science | 0.004 | 0.011 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.134 | 0.137 |
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".