Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/CENL-Network-Group-AI/awesome-list

Awesome AI in Libraries
https://github.com/CENL-Network-Group-AI/awesome-list

List: awesome-list

Last synced: about 1 month ago
JSON representation

Awesome AI in Libraries

Awesome Lists containing this project

README 

        

# Awesome AI in Libraries [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)



Libraries hold an increasing amount of digital data that can be extracted, analysed and processed using different AI methods for different use cases. Some libraries manage this internally, others set up projects and others yet have a dedicated labs environment.



Please feel free to populate this list with your project or initiative ([how-to](https://github.com/sindresorhus/awesome/blob/main/contributing.md)) or drop an email to [email protected] to inform us about it.



## Content

* [Training](#training-for-GLAM-practitioners)

* [AI Initiatives](#ai-initiatives)

* [Community Resources](#community-resources)

  * [Other Awesome Lists](#other-awesome-lists)



## Training for GLAM practitioners

- [Programming Historian](https://programminghistorian.org/)

- [Library Carpentry](https://librarycarpentry.org/)



CENL "AI in Libraries" webinars serie: see the 2023 presentations on the [CENL web site](https://www.cenl.org/network-group-ai-in-libraries-webinars-2023/).



## AI Initiatives in Europe



### Research projects

- [NewsEye](https://www.newseye.eu/), funded by the European Union’s Horizon 2020 research and innovation programme, is a research project advancing the state of the art and introducing new concepts, methods and tools for digital humanities by providing enhanced access to historical newspapers. NewsEye makes use of AI approaches for document analysis, OCR, text analysis.

- [Impresso](https://impresso-project.ch/) (EPFL-DHLAB, UUZH-CL, C2DH). The objective of the project "Media monitoring of the past. Mining 200 years of historical newspapers" is to enable critical text mining of newspaper archives with the implementation of computational linguistics tools to extract, process, link, and explore data from print media archives.

- [Living with Machines](https://livingwithmachines.ac.uk/) (Turing Institute, British Library) is a research project that rethinks the impact of technology on the lives of ordinary people during the Industrial Revolution



### Internal projects

- **National Library of Finland**:

  - [Automatic description of digital data](https://www.cenl.org/national-library-finland-high-performance-digitisation-giving-a-boost-to-the-description-of-digital-data/) using an intelligent annotation pipeline for semi-automated annotation (adding metadata) and enrichment of archived material, such as newspapers, books and official documents.

  - [Annif](https://annif.org/): tool for automated subject indexing and classification

- **Bibliothèque nationale de France**: 

  - [GallicaPix](https://gallicapix.bnf.fr/), hybrid retrieval of heritage images with use of trained classification models and commercial AI APIs.

  - [GallicaSnoop](https://snoop.inria.fr/bnf/login), visual similarity engine

  - *See more projects [here](https://github.com/CENL-Network-Group-AI/awesome-list/blob/main/BnF.md)*

- **National Library of Norway**:

  - Machine Learning and the Dewey Decimal ([conference presentation](https://nkos-eu.github.io/2019/content/NKOS2019-presentation-wetjen.pdf), NKOS 2019; [conference paper](http://library.ifla.org/id/eprint/2216), IFLA WLIC 2018)

  - [NoTraM - Norwegian Transformer Model](https://github.com/NBAiLab/notram), a transformer-based model for the Norwegian language

- **Helsinki Central Library Oodi**:  [Headai](https://medium.com/headai-customer-stories/customer-story-oodi-1d1ef2554bb6), a virtual information assistant 

- **Royal Library of Belgium**: [Cataloguing Books](https://www.realdolmen.com/en/case-study/artificial-intelligence-helps-royal-library-of-belgium), a tool developed in Windows Powerapps, that detects metadata based on title page (title, author, publisher, and so on). Future developments: detection of type of page (is the page to be treated a title page, or a colophon, or back cover), and based on the results, other actions (title pages: metadata title, author, publisher), colophon (detect metadata isbn, legal deposit number, names, publisher), and back cover (subject indexing)

- **Swiss National Library**: [Automatic Classification of e-Dissertations](https://github.com/CENL-Network-Group-AI/awesome-list/blob/main/presentations/CENL_AI_Marcel_Gygli.pdf) The National Library of Switzerland receives one copy each of dissertations produced in Switzerland from university libraries, a large proportion of which are now digital. The dissertations are to be classified into one of the approximately 100 subject groups. The aim of this project is to test open source algorithms that automatically classify the theses. 

- **German National Library (DNB)**: [Automatic subject indexing with Annif](https://swib.org/swib21/slides/03-02-uhlmann.pdf)

- **National Library of Luxembourg**: 

  - [Fine grained language identification in multilingual corpus with OCR errors](https://github.com/CENL-Network-Group-AI/awesome-list/blob/main/presentations/CENL_AI_Yves_Maurer.pdf) The project describes how the BnL identified 18 different languages in a 8 million articles collection, ranging from majority languages like French and German to minority cases like Latin or Esperanto using a combination of different existing models and dictionaries.

  - [OCR post-correction](https://github.com/natliblux/nautilusocr) This project aims at enhancing the OCR quality of original METS/ALTO packages.



### Tools and services 

- [Transkribus](https://readcoop.eu/transkribus/): a platform for the transcription, recognition and searching of historical documents

- [Visual Geometry Group](https://www.robots.ox.ac.uk/~vgg/), university of Oxford: computer vision tools for Digital Humanities

- [DANE (Distributed Annotation ‘n’ Enrichment)](https://dane.readthedocs.io/en/latest/index.html), Netherlands institute of Sound and Vision 



## Community Resources



### Other Awesome Lists

- [Ai4lam Look Book](https://docs.google.com/presentation/d/1iWG9RpPaMlikUAe8mfVlYQeoCiNH8ct2ILFtbMI7P_o/edit#slide=id.p) : Knowledge Base of AI 

Projects in Libraries, Archives and Museums from the [ai4lam.org](https://sites.google.com/view/ai4lam) international initiative.

- [The Museums + AI Network](https://themuseumsai.network/about). List of Artificial Intelligence (AI) [initiatives in museums](https://docs.google.com/spreadsheets/d/1A7IVnucQZ0ICxYSOCjqQ1oV3xGgNzDKtIYGrk6smV7w/edit#gid=0)

- [AI:CULT - Culturally aware AI](https://www.cultural-ai.nl/projects/aicult-culturally-aware-ai)