Online evaluation for information retrieval
Online evaluation is one of the most common approaches to measure the effectiveness of an
information retrieval system. It involves fielding the information retrieval system to real users …
information retrieval system. It involves fielding the information retrieval system to real users …
[PDF][PDF] Advancements in Dueling Bandits.
The dueling bandits problem is an online learning framework where learning happens “on-
thefly” through preference feedback, ie, from comparisons between a pair of actions. Unlike …
thefly” through preference feedback, ie, from comparisons between a pair of actions. Unlike …
A click sequence model for web search
Getting a better understanding of user behavior is important for advancing information
retrieval systems. Existing work focuses on modeling and predicting single interaction …
retrieval systems. Existing work focuses on modeling and predicting single interaction …
Beyond ranking: Optimizing whole-page presentation
Modern search engines aggregate results from different verticals: webpages, news, images,
video, shopping, knowledge cards, local maps, etc. Unlike" ten blue links", these search …
video, shopping, knowledge cards, local maps, etc. Unlike" ten blue links", these search …
Meta-evaluation of online and offline web search evaluation metrics
As in most information retrieval (IR) studies, evaluation plays an essential part in Web
search research. Both offline and online evaluation metrics are adopted in measuring the …
search research. Both offline and online evaluation metrics are adopted in measuring the …
[HTML][HTML] User behavior modeling for web search evaluation
Search engines are widely used in our daily life. Batch evaluation of the performance of
search systems to their users has always been an essential issue in the field of information …
search systems to their users has always been an essential issue in the field of information …
Learning from user interactions with rankings: a unification of the field
H Oosterhuis - arXiv preprint arXiv:2012.06576, 2020 - arxiv.org
Ranking systems form the basis for online search engines and recommendation services.
They process large collections of items, for instance web pages or e-commerce products …
They process large collections of items, for instance web pages or e-commerce products …
Benchmarking news recommendations: The clef newsreel use case
The CLEF NewsREEL challenge is a campaign-style evaluation lab allowing participants to
evaluate and optimize news recommender algorithms. The goal is to create an algorithm …
evaluate and optimize news recommender algorithms. The goal is to create an algorithm …
Evaluation measures for relevance and credibility in ranked lists
Recent discussions on alternative facts, fake news, and post truth politics have motivated
research on creating technologies that allow people not only to access information, but also …
research on creating technologies that allow people not only to access information, but also …
A context-aware time model for web search
In web search, information about times between user actions has been shown to be a good
indicator of users' satisfaction with the search results. Existing work uses the mean values of …
indicator of users' satisfaction with the search results. Existing work uses the mean values of …