The Information and Language Processing Systems group is part of the Informatics Institute of the University of Amsterdam. Our research is aimed at intelligent information access, especially in the face of massive amounts of information. We work on finding and analyzing content (information retrieval, machine translation, language technology), the analysis of structural information (social networks, linked data) and the analysis of user behavior (self-learning search, log analysis, user studies).

We combine fundamental, experimental and applied research, and we do so using a broad range of textual data, data from the web or enterprises, edited or user generated, or obtained from (automatic) transcriptions of audio or video. We are involved in a large number of projects with other groups, both within and outside academia. Our research is funded by NWO, KNAW, the EU and through a range of public-private partnerships.

Recent News

Google Faculty Research Award for Evangelos Kanoulas

Evangelos Kanoulas has been awarded a Google Faculty Research Award for his proposal ‘Session-based Personalization: Analysis and Evaluation’, to conduct research on personalizing search engine results on the basis of user interactions with the search engine on the current session.

The Google Research Awards Program received 805 strong proposals and funded 113 of them, with only 3 of them in the fields of Information retrieval, extraction and organization (including semantic graphs).

More information

Adith Swaminathan and Tobias Schnabel visit ILPS

Adith Swaminathan and Tobias Schnabel are visiting for one year. They are both PhD students at Cornell University working in the intersection of machine learning and information access. Adith’s main focus is on batch learning from bandit feedback using counterfactual risk estimators, developing the learning algorithms and the underlying theory for principled learning from logged interaction data. Tobias works on principled methods for evaluation, including the evaluation of embedding methods for text and the use of propensity scoring for reducing bias in recommender-system evaluation due to self-selection effects.

Invited talk by Hylke Buisman

Friday 18 September 2015, 14:00-15:00, room C1.112

Speaker: Hylke Buisman (Google, Zurich, Switzerland)

Title: Natural Language Understanding with the Knowledge Graph

Abstract: In this talk I will give an overview of the work at Google on Natural Language Understanding using Google’s Knowledge Graph. This talk will start with an overview of the applications, and then talk about various technical challenges, such as entity reconciliation and semantic parsing.

Invited talk by Claudia Hauff

Friday 18 September 2015, 16:00-17:00, room C1.112

Speaker: Claudia Hauff, TU Delft

Title: Searching & Learning

Abstract: Learning to search and searching as learning are two distinct but related activities users are busy with every day. In this talk I will first present our findings on how to aid users in learning how to formulate better queries by providing examples of high-quality queries interactively during search sessions. Based on several controlled user studies we collected quantitative and qualitative evidence that shows: (i) users are able to identify and abstract qualities of queries that make them highly effective, (ii) after seeing high-quality example queries users are able to themselves create queries that are highly effective, and, (iii) those queries look similar to expert queries as defined in the literature. In the second part, I will move on to searching as learning and present a set of initial research ideas that we are currently investigating as part of TU Delft’s initiative on MOOCs, where learning & searching naturally meet.

SEA: User Behaviour and Topical Diversity

The last Friday of September, we’ll start again with a new season of Search Engines Amsterdam (SEA). We will have two talks followed by drinks.

Andreas Brückner (SDL Fredhopper) will talk about “Search behavior in e-commerce search” and Hosein Azarbonyad (ILPS) will talk about “Measuring Topical Diversity of Text Documents Using Parsimonious Topic Models”.

Science Park 904, Room A1.10. Time: Friday, September 25, 16-17hrs with drinks afterwards.

Signup at Meetup

SEA: Search Engines Amsterdam is brought to you by Amsterdam Data Science.