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

Invited talk by Shane Culpepper

Shane Culpepper (RMIT University, Melbourne, Australia) will give a talk entitled “Efficient Location-aware Web Search” on February 1, 16-17hrs, Room G4.15.

Mobile search is quickly becoming the most common mode of search on the internet. This shift is driving changes in user behaviour, and search engine behaviour. Just over half of all search queries from mobile devices have local intent, making location-aware search an increasingly important problem. In this work, we explore the efficiency and effectiveness of two general types of geographical search queries, range queries and k nearest neighbor queries, for common web search tasks. We test state-of-the-art spatial-textual indexing and search algorithms for both query types on two large datasets. Finally, we present a rank-safe dynamic pruning algorithm that is simple to implement and use with current inverted indexing techniques. Our algorithm is more efficient than the tightly coupled best-in-breed hybrid indexing algorithms that are commonly used for top-k spatial textual queries, and more likely to find relevant documents than techniques derived from range queries.

Invited talk by Mark Carman

Mark Carman (Monash University, Australia) will give a talk on “Investigating performance and scalability issues for rank learning with regression tree ensembles” on January 11, 2016 at 16.00hrs, room C1.112.

When ranking Web pages against user queries (and their associated context), there exist a large number of signals that can be leveraged to determine relevance. Such signals include the similarity between the user’s query (/profile) and various parts of the document or related anchor-text, the recency of the content, spam scores, etc. Rank learning algorithms provide a coherent framework for determining the best way to combine these signals in order to maximise retrieval performance. As such, they have become a crucial component of current Information Retrieval infrastructure. State-of-the-art rank-learning techniques discover non-linear combinations of features and are mostly based on ensembles of regression trees, using either bagged & randomised regressors (as in Random Forests) or boosted ensembles (as in Gradient-boosted methods). With an interest in both the performance and scalability of these algorithms, we investigate the importance of three different aspects: (i) the number of negative examples used to train the algorithm, (ii) the size of the subsample used to learn individual trees, and (iii) the type of objective function used to recursively partition the feature space.