In the run-up to the Buma Music meets Tech Award at Noorderslag 2015, an update to our music discovery demonstrator Streamwatchr has gone live. An improved interface that is easier on your device’s battery life, some new functionality and a Twitter bot called @lyricswatchr are the most important ingredients of the update.
Author: mdr
WSDM 2015 paper on large-scale online ranker evaluation online
Our WSDM 2015 paper “mergeRUCB: A method for large-scale online ranker evaluation” by Masrour Zoghi, Shimon Whiteson and Maarten de Rijke is online now. A key challenge in information retrieval is that of on-line ranker evaluation: determining which one of a finite set of rankers performs the best in expectation on the basis of user clicks on…
Verder gaan dan Google
Vandaag verscheen een kort stukje in De Telegraaf over recente ontwikkelingen in zoekmachine-technologie.
Sneller lerende zoekmachines in het nieuws
Een nieuwsbericht over sneller lerende zoekmachines, naar aanleiding van een CIKM 2014 artikel van Anne Schuth, Floor Sietsma, Shimon Whiteson, Damien Lefortier en Maarten de Rijke (Multileaved comparisons for fast online evaluation) staat op de UvA nieuws-site. Zie hier.
SEA on Meetup
We’ve just created an “official” Meetup for SEA: Search Engines Amsterdam, with the idea of expanding the reach of the meetings. Join the Meetup group at http://www.meetup.com/SEA-Search-Engines-Amsterdam/ and RSVP to the SEA Meetup this Friday.
CIKM 2014 paper on online exploration for detecting shifts in fresh intent
Our CIKM 2014 paper on “Online exploration for detecting shifts in fresh intent” by Damien Lefortier, Pavel Serdyukov and Maarten de Rijke is available online now. In web search, recency ranking refers to the task of ranking documents while taking into account freshness as one of the criteria of their relevance. There are two approaches to recency…
CIKM 2014 paper on time-aware rank aggregation for microblog search online
Our CIKM 2014 paper “Time-aware rank aggregation for microblog search” by Shangsong Liang, Zhaochun Ren, Wouter Weerkamp, Edgar Meij and Maarten de Rijke is available online now. In the paper we tackle the problem of searching microblog posts and frame it as a rank aggregation problem where we merge result lists generated by separate rankers so as…
Big data en forensische wetenschap
Naar aanleiding van de publicatie van de ‘elementaire deeltjes Informatie en Forensische wetenschap vindt er een debat plaats met Zeno Geradts (NFI/UvA), Maarten de Rijke (UvA), Ton Siedsma (Bits of Freedom), Maurits Martijn (De Correspondent), op dinsdag 21 oktober, 17-19u, Spui 25, Amsterdam.
CIKM 2014 paper on time-sensitive personalized query auto-completion online
Our CIKM 2014 paper “Time-Sensitive Personalized Query Auto-Completion” by Fei Cai, Shangsong Liang and Maarten de Rijke is online now. Query auto-completion (QAC) is a prominent feature of modern search engines. It is aimed at saving user’s time and enhancing the search experience. Current QAC models mostly rank matching QAC candidates according to their past popularity, i.e.,…
One week to go: AMS Data #1: Coffee and Data Science
A week from today, we’ll see the launch of a new Amsterdam Data Science event series: AMS Data: Coffee and Data Science. What is a better way to start your morning than with data and coffee? Amsterdam Data Science is organizing an event on September 25 (9:00 – 12:00pm) to bring the Amsterdam area data science…