---
title: "Latin — papers — Elamur Research"
description: "Latin: 13 papers of the Elamur Research library, the most cited first. Among them: The Annotation Guidelines of the Latin Dependency…"
canonical: "https://research.elamur.ai/free/en/topics/latin/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/topics/latin/)

[home](https://md.research.elamur.ai/free/en/) / [topics](https://md.research.elamur.ai/free/en/topics/) / Latin

# Latin

13 papers · the most cited first · [all topics](https://md.research.elamur.ai/free/en/topics/)

The language of Rome and of Europe's scholarship, its texts and the tools that read them.

A survey · about 6 minutes to read · every paper named here has its own page in this library

**In this article**

1. [What it is](#a-what-it-is)
2. [History and milestones](#a-history-and-milestones)
3. [Main problems and methods](#a-main-problems-and-methods)
4. [Landmark papers in this library](#a-landmark-papers-in-this-library)
5. [People](#a-people)
6. [Institutions and places](#a-institutions-and-places)
7. [Open questions](#a-open-questions)
8. [Neighbouring topics](#a-neighbouring-topics)

Latin was the language of Rome and, for well over a millennium after the empire, the shared written language of European law, theology, science and scholarship. Its corpus therefore runs from the classical poets and orators through late antique and medieval prose to early modern books in which Latin passages sit inside vernacular text. That breadth makes Latin unusual among historical languages: there is a great deal of text, but it varies enormously in period, genre and spelling.

Computational work on Latin has a famous origin. In 1949 the Jesuit scholar Roberto Busa began, with IBM's support, to put the works of Thomas Aquinas on punched cards, the project that became the Index Thomisticus and is often cited as the beginning of humanities computing. The papers under this topic show where that line has led: dependency treebanks with shared annotation rules, linked open data that joins corpora and lexica, shared tasks on parsing and named entities, and language models applied to manuscripts, legal texts and printed books.

## What it is

The topic covers research on Latin texts and on tools that analyse them: annotation schemes, treebanks, lemmatisers, parsers, entity recognisers, retrieval and alignment systems, and lexical and narrative resources. It also includes linguistic and cultural studies in which Latin is a contact language, as in the history of English vocabulary or of Maltese.

Latin shares its classical setting with [Ancient Greek](https://md.research.elamur.ai/free/en/topics/ancient-greek/), and the two meet in cross-lingual retrieval and alignment. The emphasis differs, though: Latin work here is closer to [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/), [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) and [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), and to [Legal AI](https://md.research.elamur.ai/free/en/topics/legal-ai/) through Roman and medieval legal sources. Every paper here stands on the [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) shelf; many also belong to [Natural language processing](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/), [History & humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/history/) and [Law](https://md.research.elamur.ai/free/en/shelves/social-sciences/law/).

## History and milestones

After the Index Thomisticus, the next turning point was syntactic annotation. In the late 2000s the Perseus Project's Latin Dependency Treebank, built on classical authors, and the Index Thomisticus Treebank, built on Aquinas, adopted common guidelines derived from the Prague Dependency Treebank. Other Latin treebanks followed, among them PROIEL, the Late Latin Charter Treebank and UDante, and all were converted into Universal Dependencies. From 2020 the EvaLatin shared tasks, held with the LT4HALA workshops on historical and ancient languages, gave the field common evaluations for lemmatisation, tagging and later parsing. Alongside, the LiLa project built a knowledge base linking Latin resources through a shared bank of lemmas. In this library the oldest paper is the 2008 guidelines paper, still the most cited; most of the rest appeared in 2026, many from the latest LT4HALA workshop.

Landmark papers on this topic: the 8 most cited, in time The 8 most cited papers on this topic span 2008–2026; the dot grows with the citations.

**The numbers**

| Paper | Citations |
| --- | --- |
| [2008 — The Annotation Guidelines of the Latin Dependency Treebank and Index Thomisticus Treebank: the Treatment of some specific Syntactic Constructions in Latin](https://md.research.elamur.ai/free/en/papers/bamman-2008-annotation-guidelines-latin-dependency-treebank/) | 23 |
| [2022 — The Index Thomisticus Treebank as Linked Data in the LiLa Knowledge Base](https://md.research.elamur.ai/free/en/papers/mambrini-2022-index-thomisticus-treebank-as-linked/) | 9 |
| [2024 — The church and the manor: Assessing and comparing the effects of language contact on two Middle English lexical domains](https://md.research.elamur.ai/free/en/papers/mambelli-2024-church-manor-assessing-comparing-effects/) | 1 |
| [2026 — Contextual Probing for Low-Resource Named Entity Recognition in Latin](https://md.research.elamur.ai/free/en/papers/trusca-2026-contextual-probing-low-resource-named/) | 1 |
| [2026 — Gretino: A Greek and Latin Dataset to Benchmark Retrieval Systems in Classical Languages](https://md.research.elamur.ai/free/en/papers/toyin-2026-gretino-greek-latin-dataset-benchmark/) | 1 |
| [2026 — Language Models for the Restoration of Latin Legal Manuscripts](https://md.research.elamur.ai/free/en/papers/zhang-2026-language-models-restoration-latin-legal/) | 1 |
| [2026 — THIVLVC: Retrieval Augmented Dependency Parsing for Latin](https://md.research.elamur.ai/free/en/papers/pommeret-2026-thivlvc-retrieval-augmented-dependency-parsing/) | 1 |
| [2026 — UppsalaNLP at EvaLatin 2026: Multilingual parsing for Latin](https://md.research.elamur.ai/free/en/papers/stymne-2026-uppsalanlp-evalatin-2026-multilingual-parsing/) | 1 |

Papers on this topic by year 13 dated papers from 2008 to 2026; the busiest year is 2026 with 9, and 85% of them appeared in 2018 or later.

**The numbers**

| Year | Papers |
| --- | --- |
| 2026 | 9 |
| 2024 | 1 |
| 2022 | 1 |
| 2011 | 1 |
| 2008 | 1 |

## Main problems and methods

The tasks here fall into a few groups.

- **Annotation and parsing.** Latin word order is free and phrases are often discontinuous, which favours dependency rather than constituency analysis. Hard constructions include the ablative absolute, the accusative with infinitive and the gerundive. Recent parsing work asks how far training-data choice and genre matter, with poetry much harder than prose.
- **Lemmatisation and terminology.** Specialised texts such as Justinian's Digest challenge general lemmatisers; one study pairs a neural lemmatiser with an LLM post-correction step.
- **Named entities** in low-resource settings, where annotated data is scarce.
- **Restoration and detection.** Filling gaps in damaged medieval deeds, and finding Latin passages inside 18th-century English books with noisy OCR.
- **Linking resources.** Publishing treebanks and narrative databases as linked open data so that tokens, lemmas and annotations can be queried together.
- **Cross-lingual retrieval** between Latin and Greek.

Methodologically the papers span rule-based annotation design, ontology modelling (RDF, OntoLex-Lemon, POWLA, OLiA, CIDOC CRM), fine-tuned encoders such as LaBERTa, LatinBERT and PhilBERTa, multilingual parsers built on XLM-RoBERTa, and large language models used for correction, refinement or zero-shot detection. A recurring finding is that LLMs help most where the baseline is weak or ambiguous, and that single-reference evaluation can penalise defensible analyses when treebanks disagree among themselves. These links tie the topic to [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) and [Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/).

## Landmark papers in this library

**Shared treebank guidelines.** [The Annotation Guidelines of the Latin Dependency Treebank and Index Thomisticus Treebank: the Treatment of some specific Syntactic Constructions in Latin](https://md.research.elamur.ai/free/en/papers/bamman-2008-annotation-guidelines-latin-dependency-treebank/) (2008) adapted the Prague scheme to Latin, following Pinkster's grammar, and set out how to annotate the characteristic Latin constructions. Because both treebanks used one manual, classical and medieval data could be combined despite roughly thirteen centuries between them; the two projects differed only on ellipsis.

**A treebank as linked data.** [The Index Thomisticus Treebank as Linked Data in the LiLa Knowledge Base](https://md.research.elamur.ai/free/en/papers/mambrini-2022-index-thomisticus-treebank-as-linked/) (2022) models every layer of the largest Latin treebank as an RDF graph, attaching both the original and the UD analyses to the same tokens and linking lemmas to LiLa's Lemma Bank, so the treebank can be queried with SPARQL together with lexical resources.

**Entities by probing.** [Contextual Probing for Low-Resource Named Entity Recognition in Latin](https://md.research.elamur.ai/free/en/papers/trusca-2026-contextual-probing-low-resource-named/) (2026) substitutes known example entities into each position and lets a masked model judge the fit; the score works as a zero-shot tagger and as a tie-breaker for a fine-tuned one, and the system ranked near the top of the shared task.

**Classical retrieval.** [Gretino: A Greek and Latin Dataset to Benchmark Retrieval Systems in Classical Languages](https://md.research.elamur.ai/free/en/papers/toyin-2026-gretino-greek-latin-dataset-benchmark/) (2026) offers synthetic and authentic query sets for semantic search in Latin, Greek and across both.

**Restoring manuscripts.** [Language Models for the Restoration of Latin Legal Manuscripts](https://md.research.elamur.ai/free/en/papers/zhang-2026-language-models-restoration-latin-legal/) (2026) fills gaps in Bolognese notarial deeds with a decoding pipeline that handles damage cutting through words; it beats simple baselines clearly but is best used to suggest readings to paleographers.

**Two parsing systems.** [THIVLVC: Retrieval Augmented Dependency Parsing for Latin](https://md.research.elamur.ai/free/en/papers/pommeret-2026-thivlvc-retrieval-augmented-dependency-parsing/) (2026) has an LLM revise a UDPipe parse using similar retrieved sentences and the UD guidelines, with large gains on poetry. [UppsalaNLP at EvaLatin 2026: Multilingual parsing for Latin](https://md.research.elamur.ai/free/en/papers/stymne-2026-uppsalanlp-evalatin-2026-multilingual-parsing/) (2026) keeps the parser fixed and varies the training treebanks, adding other historical languages; it led on prose but not on poetry.

**Latin inside English books.** [Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark](https://md.research.elamur.ai/free/en/papers/wu-2026-detecting-latin-historical-books-large/) (2026) annotates pages from eighteenth-century books by usage type and finds that models detect Latin reliably, though often from surface cues.

**Other contributions.** [Evaluating Latin and Ancient Greek Sentence Alignment through Parallel Sentence Mining](https://md.research.elamur.ai/free/en/papers/reichbauer-2026-evaluating-latin-ancient-greek-sentence/) tests encoders on finding Boethius' translations of Aristotle; [From Lemmatization to Legal Terminology: Assessing an Hybrid Pipeline on Justinian's Digest](https://md.research.elamur.ai/free/en/papers/marongiu-2026-lemmatization-legal-terminology-assessing-hybrid/) measures lemmatisation against a legal glossary goal; [Latin Represented Speech (LaReS): Linking LiLa and the DICES Database](https://md.research.elamur.ai/free/en/papers/mambrini-2026-latin-represented-speech-lares-linking/) ties speeches in the Aeneid to LiLa tokens. Beyond NLP, [The church and the manor: Assessing and comparing the effects of language contact on two Middle English lexical domains](https://md.research.elamur.ai/free/en/papers/mambelli-2024-church-manor-assessing-comparing-effects/) studies Latin and French loans in English, and [The Fusion of Semitic and Latin Cultures in the Language and Literature of Malta](https://md.research.elamur.ai/free/en/papers/friggieri-2026-fusion-semitic-latin-cultures-language/) traces the Romance layer in Maltese.

Citations of the papers on this topic, by when they were published Papers published in 2005–2009 gather 61% of the 38 citations of the papers on this topic.

**The numbers**

| Published | Papers and their citations |
| --- | --- |
| 2025–2029 | 9 papers, 5 citations |
| 2020–2024 | 2 papers, 10 citations |
| 2010–2014 | 1 papers, 0 citations |
| 2005–2009 | 1 papers, 23 citations |

## People

Authors with the most papers on this topic Marco Passarotti leads with 2 papers; the 12 authors shown wrote 14 of the papers on this topic between them, counting each paper once per author.

**The numbers**

| Author | Papers here · their citations |
| --- | --- |
| [Marco Passarotti](https://md.research.elamur.ai/free/en/authors/marco-passarotti/) | 2 papers · 32 citations |
| [Francesco Mambrini](https://md.research.elamur.ai/free/en/authors/francesco-mambrini/) | 2 papers · 9 citations |
| [David Bamman](https://md.research.elamur.ai/free/en/authors/david-bamman/) | 1 paper · 23 citations |
| [Giovanni Colavizza](https://md.research.elamur.ai/free/en/authors/giovanni-colavizza/) | 1 paper · 1 citation |
| [Hawau Olamide Toyin](https://md.research.elamur.ai/free/en/authors/hawau-olamide-toyin/) | 1 paper · 1 citation |
| [Sara Stymne](https://md.research.elamur.ai/free/en/authors/sara-stymne/) | 1 paper · 1 citation |
| [Tim Van de Cruys](https://md.research.elamur.ai/free/en/authors/tim-van-de-cruys/) | 1 paper · 1 citation |
| [Alexander Fraser](https://md.research.elamur.ai/free/en/authors/alexander-fraser/) | 1 paper · 0 citations |
| [Eetu Mäkelä](https://md.research.elamur.ai/free/en/authors/eetu-makela/) | 1 paper · 0 citations |
| [Lidia Pivovarova](https://md.research.elamur.ai/free/en/authors/lidia-pivovarova/) | 1 paper · 0 citations |
| [Paola Marongiu](https://md.research.elamur.ai/free/en/authors/paola-marongiu/) | 1 paper · 0 citations |
| [Shu Okabe](https://md.research.elamur.ai/free/en/authors/shu-okabe/) | 1 paper · 0 citations |

- [Marco Passarotti](https://md.research.elamur.ai/free/en/authors/marco-passarotti/), of the Università Cattolica del Sacro Cuore and Ghent University, leads the author list here: co-author of the 2008 guidelines and of the LiLa treebank work, and principal investigator of the LiLa project.
- [Francesco Mambrini](https://md.research.elamur.ai/free/en/authors/francesco-mambrini/), from the same institutions, models Latin treebanks and narrative data as linked open data.
- [David Bamman](https://md.research.elamur.ai/free/en/authors/david-bamman/), now at the University of California, Berkeley, first author of the 2008 guidelines from his time with the Perseus Project.
- [Sara Stymne](https://md.research.elamur.ai/free/en/authors/sara-stymne/) of Uppsala University works on multilingual and historical parsing.
- [Tim Van de Cruys](https://md.research.elamur.ai/free/en/authors/tim-van-de-cruys/) of KU Leuven is senior author of the entity-probing study.
- [Paola Marongiu](https://md.research.elamur.ai/free/en/authors/paola-marongiu/), at the Institute for Computational Linguistics "A. Zampolli" in Pisa, studies lemmatisation of legal Latin.
- [Eetu Mäkelä](https://md.research.elamur.ai/free/en/authors/eetu-makela/) and [Lidia Pivovarova](https://md.research.elamur.ai/free/en/authors/lidia-pivovarova/) of the University of Helsinki, with [Yu Wu](https://md.research.elamur.ai/free/en/authors/yu-wu/), wrote the Latin-detection benchmark.
- [Hawau Olamide Toyin](https://md.research.elamur.ai/free/en/authors/hawau-olamide-toyin/), [Alexander Fraser](https://md.research.elamur.ai/free/en/authors/alexander-fraser/) and [Shu Okabe](https://md.research.elamur.ai/free/en/authors/shu-okabe/) contributed the Latin–Greek retrieval and mining work.

## Institutions and places

Italy and Belgium lead, through the LiLa group at the [Università Cattolica del Sacro Cuore](https://md.research.elamur.ai/free/en/universities/universita-cattolica-del-sacro-cuore/) and [Ghent University](https://md.research.elamur.ai/free/en/universities/ghent-university/), and through [KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/), the [Institute for Computational Linguistics "A. Zampolli"](https://md.research.elamur.ai/free/en/labs/institute-for-computational-linguistics-a-zampolli/) and the [National Research Council](https://md.research.elamur.ai/free/en/ngos/national-research-council/). Further contributions come from [Uppsala University](https://md.research.elamur.ai/free/en/universities/uppsala-university/), the [University of Helsinki](https://md.research.elamur.ai/free/en/universities/university-of-helsinki/) and [University of Turku](https://md.research.elamur.ai/free/en/universities/university-of-turku/), the [Technical University of Munich](https://md.research.elamur.ai/free/en/universities/technical-university-of-munich/) and [Munich Center for Machine Learning](https://md.research.elamur.ai/free/en/universities/munich-center-for-machine-learning/), the [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) and [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/). The LT4HALA workshop at LREC is the main venue.

Where the authors on this topic work now Università Cattolica del Sacro Cuore is the current home of authors of 3 papers on this topic; counted are the authors with a page here, by their latest institution.

**The numbers**

| Institution | Papers |
| --- | --- |
| [Università Cattolica del Sacro Cuore](https://md.research.elamur.ai/free/en/universities/universita-cattolica-del-sacro-cuore/) | 3 papers |
| [Berkeley College](https://ror.org/02xewxa75) | 1 paper |
| [China Southern Power Grid](https://ror.org/03hkh9419) | 1 paper |
| [Guizhou Power Grid Co., Ltd.](https://ror.org/04n5vvh78) | 1 paper |
| [Helsinki Institute of Physics](https://ror.org/01x2x1522) | 1 paper |
| [IT University of Copenhagen](https://md.research.elamur.ai/free/en/universities/it-university-of-copenhagen/) | 1 paper |
| [Institute for Computational Linguistics “A. Zampolli”](https://md.research.elamur.ai/free/en/labs/institute-for-computational-linguistics-a-zampolli/) | 1 paper |
| [KU Leuven](https://md.research.elamur.ai/free/en/universities/ku-leuven/) | 1 paper |
| [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/) | 1 paper |
| [Munich Center for Machine Learning](https://md.research.elamur.ai/free/en/universities/munich-center-for-machine-learning/) | 1 paper |

Countries of the authors on this topic Italy comes first: authors working there now wrote 5 papers on this topic.

**The numbers**

| Country | Papers |
| --- | --- |
| [Italy](https://md.research.elamur.ai/free/en/countries/italy/) | 5 papers |
| [Belgium](https://md.research.elamur.ai/free/en/countries/belgium/) | 1 paper |
| [China](https://md.research.elamur.ai/free/en/countries/china/) | 1 paper |
| [Denmark](https://md.research.elamur.ai/free/en/countries/denmark/) | 1 paper |
| [Finland](https://md.research.elamur.ai/free/en/countries/finland/) | 1 paper |
| [Germany](https://md.research.elamur.ai/free/en/countries/germany/) | 1 paper |
| [Sweden](https://md.research.elamur.ai/free/en/countries/sweden/) | 1 paper |
| [United Arab Emirates](https://md.research.elamur.ai/free/en/countries/united-arab-emirates/) | 1 paper |
| [United States](https://md.research.elamur.ai/free/en/countries/united-states/) | 1 paper |

Where the papers on this topic were published Workshop on Language Technologies for Historical and Ancient Languages @ LREC carries the most, 5 of 13.

**The numbers**

| Venue | Papers |
| --- | --- |
| [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/) | 5 papers |
| [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/) | 3 papers |
| [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/) | 1 paper |
| Folia Orientalia 48 | 1 paper |
| [Lexis](https://md.research.elamur.ai/free/en/venues/lexis/) | 1 paper |
| [Workshop on Linked Data in Linguistics](https://md.research.elamur.ai/free/en/venues/ldl/) | 1 paper |
| [Workshop on Natural Language Processing for Digital Humanities](https://md.research.elamur.ai/free/en/venues/nlp4dh/) | 1 paper |

## Open questions

Genre adaptation remains the clearest gap: parsers trained mostly on prose still struggle with poetry. Treebanks disagree on conventions, so scores against a single gold reference may understate good systems. Restoration and entity recognition remain far from reliable without human review, and it is unclear how much LLM corrections can be trusted in specialised domains. Linking resources also raises a modelling question of its own: how to keep textual and narrative layers apart while querying them together.

## Neighbouring topics

The closest technical neighbours are [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/), [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/), [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), [Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) and [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/). Linked data connects it to [Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/); retrieval to [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) and [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); page images to [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/). Contact studies link to [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/) and [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/).

Neighbouring topics: papers shared Evaluation & benchmarks shares the most: 3 of the 13 papers here (23%) stand on both.

**The numbers**

| Topic | Papers shared |
| --- | --- |
| [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) | 3 shared · 23% |
| [Ancient Greek](https://md.research.elamur.ai/free/en/topics/ancient-greek/) | 2 shared · 15% |
| [Legal AI](https://md.research.elamur.ai/free/en/topics/legal-ai/) | 2 shared · 15% |
| [Treebanks](https://md.research.elamur.ai/free/en/topics/treebanks/) | 2 shared · 15% |
| [Universal Dependencies](https://md.research.elamur.ai/free/en/topics/universal-dependencies/) | 2 shared · 15% |
| [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) | 1 shared · 8% |
| [English](https://md.research.elamur.ai/free/en/topics/english/) | 1 shared · 8% |
| [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/) | 1 shared · 8% |
| [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) | 1 shared · 8% |
| [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) | 1 shared · 8% |

The shelves this topic stands on Language and Linguistics: 13 of the 13 papers here.

**The numbers**

| Shelf | Papers |
| --- | --- |
| [Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) | 13 papers |
| [Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) | 10 papers |
| [Literature and Literary Theory](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/literature-and-literary-theory/) | 6 papers |
| [Anthropology](https://md.research.elamur.ai/free/en/shelves/social-sciences/anthropology/) | 1 paper |
| [Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) | 1 paper |
| [Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) | 1 paper |

## Papers (13)

1. **[The Annotation Guidelines of the Latin Dependency Treebank and Index Thomisticus Treebank: the Treatment of some specific Syntactic Constructions in Latin](https://md.research.elamur.ai/free/en/papers/bamman-2008-annotation-guidelines-latin-dependency-treebank/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**David Bamman, Marco Passarotti, Roberto Busa, et al.*2008 · 23 citations*
2. **[The Index Thomisticus Treebank as Linked Data in the LiLa Knowledge Base](https://md.research.elamur.ai/free/en/papers/mambrini-2022-index-thomisticus-treebank-as-linked/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Francesco Mambrini, Marco Passarotti, Giovanni Moretti, et al.*2022 · 9 citations*
3. **[Contextual Probing for Low-Resource Named Entity Recognition in Latin](https://md.research.elamur.ai/free/en/papers/trusca-2026-contextual-probing-low-resource-named/) [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/)**Maria Mihaela Trusca, Mark Depauw, Violet Soen, et al.*2026 · 1 citation*
4. **[Gretino: A Greek and Latin Dataset to Benchmark Retrieval Systems in Classical Languages](https://md.research.elamur.ai/free/en/papers/toyin-2026-gretino-greek-latin-dataset-benchmark/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Hawau Olamide Toyin, Federico Iezzi, Elia Scapini, et al.*2026 · 1 citation*
5. **[Language Models for the Restoration of Latin Legal Manuscripts](https://md.research.elamur.ai/free/en/papers/zhang-2026-language-models-restoration-latin-legal/) [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/)**Shibingfeng Zhang, Edoardo Caraffa, Annafelicia Zuffrano, et al.*2026 · 1 citation*
6. **[THIVLVC: Retrieval Augmented Dependency Parsing for Latin](https://md.research.elamur.ai/free/en/papers/pommeret-2026-thivlvc-retrieval-augmented-dependency-parsing/) [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/)**Luc Pommeret, Thibault Wagret, Jules Deret*2026 · 1 citation*
7. **[UppsalaNLP at EvaLatin 2026: Multilingual parsing for Latin](https://md.research.elamur.ai/free/en/papers/stymne-2026-uppsalanlp-evalatin-2026-multilingual-parsing/) [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/)**Sara Stymne*2026 · 1 citation*
8. **[The church and the manor: Assessing and comparing the effects of language contact on two Middle English lexical domains](https://md.research.elamur.ai/free/en/papers/mambelli-2024-church-manor-assessing-comparing-effects/) [Lexis](https://md.research.elamur.ai/free/en/venues/lexis/)**Gloria Mambelli, Johanna Vogelsanger*2024 · 1 citation*
9. **[Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark](https://md.research.elamur.ai/free/en/papers/wu-2026-detecting-latin-historical-books-large/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Yu Wu, Ke Shu, Jonas Fischer, et al.*2026*
10. **[Evaluating Latin and Ancient Greek Sentence Alignment through Parallel Sentence Mining](https://md.research.elamur.ai/free/en/papers/reichbauer-2026-evaluating-latin-ancient-greek-sentence/) [Workshop on Natural Language Processing for Digital Humanities](https://md.research.elamur.ai/free/en/venues/nlp4dh/)**Sebastian Reichbauer, Shu Okabe, Alexander Fraser*2026*
11. **[From Lemmatization to Legal Terminology: Assessing an Hybrid Pipeline on Justinian's Digest](https://md.research.elamur.ai/free/en/papers/marongiu-2026-lemmatization-legal-terminology-assessing-hybrid/) [Workshop on Language Technologies for Historical and Ancient Languages @ LREC](https://md.research.elamur.ai/free/en/venues/lt4hala/)**Paola Marongiu, Eva Sassolini*2026*
12. **[Latin Represented Speech (LaReS): Linking LiLa and the DICES Database](https://md.research.elamur.ai/free/en/papers/mambrini-2026-latin-represented-speech-lares-linking/) [Workshop on Linked Data in Linguistics](https://md.research.elamur.ai/free/en/venues/ldl/)**Francesco Mambrini*2026*
13. [**The Fusion of Semitic and Latin Cultures in the Language and Literature of Malta Folia Orientalia 48**Oliver Friggieri*2011*](https://md.research.elamur.ai/free/en/papers/friggieri-2026-fusion-semitic-latin-cultures-language/)

Updated 24 October 2026

- [← previous topic Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/)
- [next topic → Summarization](https://md.research.elamur.ai/free/en/topics/summarization/)
- [↑ back to topics](https://md.research.elamur.ai/free/en/topics/)