Discovering key concepts in verbose queries

295 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, background): “, Bendersky and Croft [2008], though these usually refer to sentence-length descriptions of information needs as opposed to paragraph-length narratives.”
Latent entity space: a novel retrieval approach for entity-bearing queries (2015, methodology): “This is known as the language modeling (LM) approach (Ponte and Croft 1998). n ( w , q ) denotes the number of occurrences of w in q .”
Modeling and solving term mismatch for full-text retrieval (2012, methodology): “Looking closely, Bendersky and Croft (2008) viewed a concept as a probabilistic-AND combination of some of the original query terms, a bag of words conjoined together, producing one single belief or relevance probability for each resultant document.”
mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval (2025, unknown): “Much previous work has examined the relationship between query length and model performance [7–9 , 20 ].”