Science is not only built on the shoulders of giants. It is also built on the shoulders of many volunteers that contribute their data, opinions or judgements, in order to collect sizable datasets for testing and training. Just look at TREC or CLEF competitions, the SpamAssassin Public Corpus, the images and tag judgements contributed to Alipr, and many, many more. So we need your help:
A reference Web dataset for learning to rank using click-through data -- help with relevance assessment
Learning to rank is a very important research field in Web search where machine learning techniques are employed to improve the ranking of results returned by search systems. One of the best ways of learning to rank is by observing users behaviors, which requires usage data. The lack of a publicly available dataset containing click-through data makes researches in this topic (when using click-through data) limited to industrial research groups.
TodoCL is a horizontal search engine which covers the Chilean Web, running since April 2000. As a contribution for science, the company will make available for research a series of data for the most intensive period of use of the search engine. For composing the relevance data we have prepared a relevance assessment experiment.
We are looking for people to help with the relevance assessment task, which consists on judging whether Web pages are relevant for an associated query. More information about the relevance assessment may be found here: http://grupoweb.upf.es/~cmiddlet/todocl_assessment/.
- OKKAM Entity Identification Experiment
The OKKAM European Project (http://fp7.okkam.org) is conducting a survey to investigate how people describe entities such as persons, organizations, locations, events and artefacts. We are currently looking for volunteers to participate in our experiment. If you would like to participate, then just click on the link below. After participating in this experiment, you can choose whether you would like to take part in our lottery.
We will be giving away an iPod among the participants who completed the questionnaire and opt to provide us with their contact details. On the following page you will find more information on the experiment and the instructions: http://okkam.dit.unitn.it/participant-form/.
- Flickling: An online game for searching Flickr across language boundaries
FlickLing is an online game developed as part of the iCLEF evaluation initiative for Interactive Multilingual Information Access systems. If you are interested in the motivation for this game, visit the iCLEF web page. If you need assistance with the interface or regarding your participation in iCLEF, please email
. We'll be happy to help.
With FlickLing you can query the Flickr image database in your own preferred language, and retrieve results with images annotated in several languages. From a given query, FlickLing is able to automatically translate into several languages, remembers your favorite translations and shows translation suggestions before retrieving a list of relevant images.
More information in: http://soporte1.lsi.uned.es/flickling/help_en.html