Now available as a Python package, iText2KG has been accepted at the 2024 International Web Information Systems Engineering (WISE) Conference in Qatar. github.com/AuvaLab/itex...
Incremental Knowledge Graphs Constructor Using Large Language Models - AuvaLab/itext2kg
With Yassir Lairgi et al. we introduced the iText2KG, a zero-shot method for incremental knowledge graph construction with resolved entities and relations using LLM. arxiv.org/abs/2409.03284
Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible,...
Learn to work with big historical data from newspapers & maps at a 3-day workshop in Lancaster (UK). June 5-7 2024. Taught by Living w/Machines folks: @npedrazzini.bsky.socialforms.office.com/e/HnKjET1dAs
Announcing that we are on our way to solve a long standing issue of document processing: correction of OCR mistakes. Pleias publishes the largest dataset to date with automated OCR correction, 1 billion words in English, French, German and Italian huggingface.co/datasets/Ple...
The 'Call for Papers' for CHR2024 is out! 📝 Submission deadline is July 8. There have been some changes to submission types and you can also propose workshops 🛠️. More info can be found here: 2024.computational-humanities-research.org/cfp/#CHR#cfp
The program features an exciting keynote by Beatrice Alex from University of Edinburgh on "News Media as a Lens: Exploring Neighborhood Health through Analysis of Geoparsed and Clustered Local News" and 12 presentations!
Check out the program for the 2nd International Workshop on Geographic Information Extraction from Texts (#GeoExT) at the ECIR 2024 conference in Glasgow on March 24: geo-ext.github.io/GeoExT2024/p...
Save the date: Next workshop June 3-5 at Lancaster University! Workshop 2 will cover maps + newspapers tools & data! Application form will be available soon.
We're now accepting applications for the 1st of 3 workshops introducing historians 🗃️ (& other historically-minded researchers) to tools & data created on Living w/Machines - first up, 2 days w/MapReader. April 30-May 1 in London @ the Turing Bursaries available! www.turing.ac.uk/events/sprin...
MapReader, which received the 2023 Roy Rosenweig Prize for Inno
Our paper describing the methodology for the gold standard annotation has been accepted and will be presented at the 2nd #GeoExTgeo-ext.github.io/GeoExT2024/
We just released the GeoEDdA dataset on @HuggingFace (huggingface.co/datasets/GEO...) and @ZENODO_ORG (doi.org/10.5281/zeno...) within the framework of the GEODE project (@LabexAslan): a gold standard dataset for geo-semantic annotation of Diderot & d’Alembert’s Encyclopédie.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
This model is designed for spatial role labelling, i.e. identify and classify text spans corresponding to named entities, nominal entities as well as nested named entities, spatial relations, and other relevant information within French encyclopedic entries.