Retrieval and novelty detection at the sentence level

By James Allan, Courtney Wade, Alvaro Bolivar. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2003

332 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.

Discriminative Neural Sentence Modeling by Tree-Based Convolution (2015, background): “It is related to various tasks of interest, and has attracted much attention in the NLP community (Allan et al., 2003; Su and Markert, 2008; Zhao et al., 2015).”
ReQA: An Evaluation for End-to-End Answer Retrieval Models (2019, methodology): “We opted not to evaluate BM25 on sentence-level retrieval as earlier work has shown that traditional term-based document retrieval technologies are unsuccessful when applied to sentence-level retrieval (Allan et al., 2003).”
The Evaluation of Sentence Similarity Measures (2008, methodology): “[2] proposed TF-IDF measure (simTFIDF,nov) for detecting topically similar sentences in TREC novelty track experiment.”
Learning to model relatedness for news recommendation (2011, background): “, cosine similarity, are also effective measures for novelty and redundancy detection [39, 3], it would be critical to investigate the performance of these measures with “dual-roles” in the relatedness function.”