We address a specific enterprise document search scenario, where the information need is expressed in an elaborate manner. In our scenario, information needs are expressed using a...
Krisztian Balog, Wouter Weerkamp, Maarten de Rijke
As with any application of machine learning, web search ranking requires labeled data. The labels usually come in the form of relevance assessments made by editors. Click logs can...
We give a new view on building content clusters from page pair models. We measure the heuristic importance within every two pages by computing the distance of their accessed positi...
Modeling a user’s click-through behavior in click logs is a challenging task due to the well-known position bias problem. Recent advances in click models have adopted the examin...
Botao Hu, Yuchen Zhang, Weizhu Chen, Gang Wang, Qi...
The domain-specific track evaluates retrieval models for structured scientific bibliographic collections in English, German and Russian. Documents contain elements (title, abstrac...