Foundations for Temporal Retrieval, Exploration and Analytics in Web Archives
4./5. October 2018
Significant parts of our cultural heritage are produced on the Web, yet only insufficient opportunities exist for accessing and exploring the past of the Web. While the easy accessibility to the current Web is a good baseline, optimal access to Web archives requires new models and algorithms for retrieval, exploration, and analytics which go far beyond what is needed to access the current state of the Web. This includes taking into account the unique temporal dimension of Web archives, structured semantic information already available on the Web, as well as social media and network information.
The workshop aims at bringing together communities involved in information retrieval, social network analysis and NLP to encourage a closer dialogue between researchers..
Workshop Program
Thursday, 04.10.2018
9:30 – 10:00 Opening Coffee
- Opening Remarks: Wolfgang Nejdl:
10:15 – 11:30 Session 1 – Collaborative Exploration and Analytics
- Ralf Krestel (HPI) – WELDA: Enhancing Topic Models by Incorporating Local Word Context
- Ujwal Gadiraju (L3S) – Analyzing and Predicting Knowledge Gain in Informational Search Sessions on the Web
13:00 – 14:30 Session 2 – Extractions, Enrichments and Representations
- Maria Koutraki (Uni Karlsruhe) – TableNet: Extracting Tables from Wikipedia
- Nicolas Tempelmeier (L3S) – Inferring Missing Categorical Information in Noisy and Sparse Web Markup
- Avishek Anand (L3S) – Scaling Word Embeddings
14:30 – 15:00 Coffee Break
15:00 – 16:30 Session 3 – Information Retrieval
- Simon Gottschalk (L3S) – Events and the generation of biographical timelines.
- Jaspreet Singh (L3S) – Interpretability in Search
- Benno Stein (Uni. Weimar) – Societal Challenges for Information Retrieval
Friday, 05.10.2018
- Michael Gertz (Uni. Heidelberg) – Information Networks: Towards Versatile Text Analysis and Exploration
- Megha Khosla (L3S) – Network embeddings Respecting Directionality
- Damianos Melidis (L3S) – Learning under feature drifts for textual streams
11:30 – 13:00 Lunch with Posters/Demo Session
- Martin Potthast (Uni. Leipzig) – A Stylometric Inquiry into Hyperpartisan and Fake News
- Vinay Setty (Uni. Stavanger) – Neural Models for News
- Christoph Hube (L3S)- Language Bias in News
14:30 – 15:00 Coffee Break
15:00 – 15:30 Panel Discussion “Ideas for Future Research”
Registration
Since the capacities of the room is limited we like to ask to register as soon as possible by sending an email with the subject “Alexandria WS Registration” to
Venue
L3S Research Center
Appelstrasse 9a, 15th Floor, Multimedia Room
30167 Hannover / Germany
Accommodation
We recommend hotel rooms in the Hotel Schlafgut (nearby L3S) and the Concorde Hotel Am Leineschloss (Old City Center).
Further Question & Information
For further questions and information please contact alexandria-info@L3S.de.