• Publications
  • Influence
Crowdsourcing for relevance evaluation
A new approach to evaluation called TERC is described, based on the crowdsourcing paradigm, in which many online users, drawn from a large community, each performs a small evaluation task.
Using crowdsourcing for TREC relevance assessment
Design and Implementation of Relevance Assessments Using Crowdsourcing
This work explores the design and execution of relevance judgments using Amazon Mechanical Turk as crowdsourcing platform, introducing a methodology for crowdsourcing relevance assessments and the results of a series of experiments using TREC 8 with a fixed budget.
A Language Modeling Approach for Temporal Information Needs
This work addresses information needs that have a temporal dimension conveyed by a temporal expression in the user’s query by integrating temporal expressions into a language modeling approach, thus making them first-class citizens of the retrieval model and considering their inherent uncertainty.
Temporal Structure
Temporal Information Retrieval: Challenges and Opportunities
The current research trends are reviewed and a number of interesting applications along with open problems are presented along with future work for this exciting field of information management.
Clustering and exploring search results using timeline constructions
This paper presents an add-on to traditional information retrieval applications in which various temporal information associated with documents are exploited to present and cluster documents along timelines and shows how temporal expressions are made explicit and used in the construction of multiple-granularity timelines.
Implementing crowdsourcing-based relevance experimentation: an industrial perspective
  • Omar Alonso
  • Computer Science
    Information Retrieval
  • 1 April 2013
This paper outlines a framework for conducting continuous crowdsourcing experiments, emphasizing aspects that should be of importance for all sorts of tasks, and illustrates the value of characteristics that can impact the overall outcome using examples based on TREC, INEX, and Wikipedia data sets.
On the value of temporal information in information retrieval
This paper shows some of the areas that can benefit from exploiting all the time information available in the content of documents to provide better search results and user experience.
Identification of top relevant temporal expressions in documents
This paper presents an approach to identify top relevant temporal expressions in documents using expression-, document-, corpus-, and query-based features, and demonstrates the effectiveness of this approach using two evaluation scenarios.