ANR-Lab seminar 'Unsupervised web page information extraction using graph models'
On June 26, at 15:00, a seminar of the International Laboratory for Applied Network Research will be held, where ANR-Lab members Georgy Novikov and Ilia Karpov will speak.
.png.(1051x591x123).png)
The task of extracting structured information from the pages of news portals, blogs, forums, etc. is an actual basic need of many researchers who analyze data from open sources. many resources do not have access programming interfaces, and the number of information sources on the topic of interest does not allow implementing a data parser for each resource manually. In this project, we use the visual representation of the page as a data source for information extraction tools and explore graph and convolutional network based approaches for content extraction.
The seminar will be held online on the Zoom platform. Registered participants will receive an email with an invitation to the videoconference.
Registration for the seminar is available via the link.
We will be glad to see everyone!