Work

The University of Amsterdam (ILPS) at TREC 2015 Total Recall Track

Year: 2016

Type: conference-paper

Abstract: We describe the participation of the University of Amsterdams ILPS group in the Total Recall track at TREC 2015. Based on the provided Baseline Model Implemention (”BMI”) we set out to provide two more baselines we can com-pare to in future work. The two methods are bootstrapped by a synthetic document based on the query, use TF/IDF features, and sample with dynamic batch sizes which depend on the per-centage of predicted relevant documents. We sample at least 1 percent of the corpus and stop sampling if a batch contains no relevant docu-ments. The methods diﬀer in the classiﬁer used, i.e. Logistic Regression and Random Forest.

Source: Data Archiving and Networked Services (DANS)

Authors: David van Dijk, Zhaochun Ren, Evangelos Kanoulas, Maarten de Rijke

Institutions: Yale University, University of Amsterdam

Language: English

Topic: Information Retrieval and Search Behavior

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Microsoft Research, Netherlands eScience Center, European Commission, Koninklijke Nederlandse Akademie van Wetenschappen, Nederlandse Organisatie voor Wetenschappelijk Onderzoek, European Social Fund

Awards: G1122843788, G1679186985, G283277720, G2861369480, G3943500150, G4878709720, G536623562, G5934986132, G6064598850, G7181669453, G7319450384, Virtual Centre of Excellence for Research in Violent Online Political Extremism, G7795256738

OpenAlex ID: W2575048215

FWCI:

Cites: 1

Cited by:

Related to: 10