Models for metasearch

By J. Aslam, Mark H. Montague. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001

849 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/d8c4d80458fb3680cf16bbb409940fb169f323bc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

Citations in the corpus

Preferences on a Budget: Prioritizing Document Pairs when Crowdsourcing Relevance Judgments (2022, methodology): “• Borda Count (Borda): Borda count [13] is a voting algorithm to compute a popularity score used to determine the winner of an election; such algorithm has also been used to combine document rankings from multiple IR systems [1, 12, 17, 22, 24].”
Learning to Rank for Information Retrieval and Natural Language Processing (2011, neutral): “Aslam & Montague [8] propose employing Borda Count in meta search.”
Learning to rank for information retrieval (2009, neutral): “This scenario is also referred to as meta search [7].”
Voting for candidates: adapting data fusion techniques for an expert search task (2006, methodology): “BM25 PL2 Fusion MAP 6MAP P@10 MAP 6MAP P@10 Votes RR BordaFuse CombANZ CombMED CombMIN CombMAX CombSUM CombMNZ expCombANZ expCombSUM expCombMNZ 0.1767 0.2002n 0.1877> 0.0335« 0.1085< 0.0673« 0.1790 0.1886> 0.1846> 0.0347« 0.1987> 0.2044n (+26”
Post Classification Label Refinement Using Implicit Ordering Constraint Among Data Instances (2015, methodology): “Borda Count (BC): Borda Count is a known rank aggregation method mostly used for aggregating votes in an election from a set of voters for a given set of candidates [18].”
Content-based visual search learned from social media (2012, methodology): “Since Borda Count is well recognized as a solid choice for combing rankings generated by multiple sources of evidence [4,89], we adopt the Borda method for our bi-concept search engine.”
Harvesting Image Databases from the Web (2007, methodology): “We found that combining the vision and text ranked lists using Borda count [1] or similar methods gave a slight improvement on average, but results were very class dependent.”
Multimodal Fusion for Video Search Reranking (2010, background): “Consequently, it is more attainable for low-level features to reliably distinguish different shots in a relatively small collection, which is the basis of proposed reranking scheme.”
Evaluation methods for unsupervised word embeddings (2015, background): “The problem now is that we usually cannot directly compare scores from different rankings (Aslam and Montague, 2001) as their scores are not guaranteed to have the same ranges.”
Feeling lucky?: multi-armed bandits for ordering judgements in pooling-based evaluation (2016, methodology): “Other possible lines of research include comparing our models with models of metasearch [1, 2], studying other types of non-stationary allocation methods, and considering bandit models whose reward is not binary (e.g., by considering non-binary relevance, or by estimating the importance of the…”
Comparative Deep Learning of Hybrid Representations for Image Recommendations (2016, methodology): “After learning the social embedding image distance metric, it can be adopted together with Borda Count method [2] to perform personalized image recommendations, as detailed in [19].”