Okapi at TREC-6 Automatic ad hoc, VLC, routing, filtering and QSDR

By S. Walker, Stephen E. Robertson, Mohand Boughanem, Gareth J. F. Jones, Karen Spärck Jones. 1997

Subfields: Information Retrieval & Search

How researchers see this paper

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

In Information Retrieval & Search

1. Jimmy J. Lin
2. Sebastian Riedel
3. Wen-tau Yih
4. Patrick Lewis
5. Gautier Izacard
6. Rodrigo Nogueira
7. Akari Asai
8. Hannaneh Hajishirzi

Citations in the corpus

• Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “33 Although results vary by domain and the specific set of information needs used for evaluation, one common finding is that either the title or the title and description concatentated together yields the best results; see, for example, Walker et al. [1997]. However, the differences in effectiveness”
• Task-aware Retrieval with Instructions (2022, background): “First, large-scale instruction-annotated datasets (Bach et al., 2022; Wang et al., 2022b) 1998), while Dai and Callan (2019, 2020) suggests that powerful BERT encoders (Devlin et al., 2019) could better incorporate such rich context.”
• Overview of the Sixth Text REtrieval Conference (TREC-6) (1997, methodology): “city6a1 Ð from City University, London (Walker et al., 1998) who explored iterative methods of term weighting with the goal of avoiding over®tting.”