Simple Techniques for Cross-Collection Relevance Feedback

10 citations recorded by the source corpus.

How researchers see this paper

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

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “re quite slim. As another example, the “covidex” team [Zhang et al., 2020a] implemented an approach that treated relevance feedback as a document classiﬁcation problem using simple linear classiﬁers [Yu et al., 2019, Lin, 2019b]. In both rounds 4 and 5, it was only narrowly beaten by a far more comp”
The Simplest Thing That Can Possibly Work: Pseudo-Relevance Feedback Using Text Classification (2019, methodology): “I R ] 18 A p r 2019 and Cormack [9] later proposed a variant where classifiers were trained on relevance judgments on a different collection for the same information need; this work was successfully reproduced by Yu et al. [27].”
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset (2020, methodology): “Instead, we implemented a robust approach that treats relevance feedback as a document clas-siﬁcation problem using simple linear classiﬁers, described in Yu et al. (2019) and Lin (2019).”