The ESSnet Web Intelligence Network (WIN) project was launched by Eurostat in 2021 and aims to develop and nurture a network of like-minded individuals to have access to the Web Intelligence Hub, where they will be able to explore an array of non-traditional data sources to accelerate the modernisation of the European Statistical System (ESS).
Building on the successful WIN webinar series delivered in 2022/2023 and 2023/2024, WIN will continue to provide a series of free webinars 2024/2025 open to all to keep the community updated on the work being carried out across the several work strands.
You can view our previous webinars on our YouTube channel.
The following webinars are now available to book on Eventbrite:
Lessons learned from Eurostat’s Deduplication Challenge, 13 May 2024
In December 2022, Eurostat launched its first deduplication challenge, that revolved around identifying potential duplicates within job postings sourced from the web.
This webinar will present the work of two teams that participated in the challenge: Spub.Fr, a collaboration between Insee and Dares, and Nins, that received the 2nd prize for reproducibility.
On the program:
- Different methods to identify duplicates in a multilingual dataset. This will include Named-Entity Recognition, transformer-based approaches to compare the similarity of the offers vector embeddings, or MinHash experimentations.
- Examples of best practices to conduct a data science project, such as the use of the Kedro framework for Python, and a presentation of the Onyxia Datalab.
For more information or to book your place visit our Eventbrite page.
For additional information on WIN, please access the project’s work packages, blogs and training pages. We have also published a project overview on the Data Science Campus website. To find out more or to get involved, contact us at ESSnet.project@ons.gov.uk.
Follow us on
