Multi-stage ranking pipelines have been a practical solution in modern search systems,
where the first-stage retrieval is to return a subset of candidate documents and latter stages …

This paper provides an extensive and thorough overview of the models and techniques
utilized in the first and second stages of the typical information retrieval processing chain …

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in
response to a query. Although the most common formulation of text ranking is search …

Retrieval and ranking models are the backbone of many applications such as web search,
open domain QA, or text-based recommender systems. The latency of neural ranking …

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage
model retrieves a candidate set of documents and one or more subsequent stages re-rank …

Latency and efficiency issues are often overlooked when evaluating IR models based on
Pretrained Language Models (PLMs) in reason of multiple hardware and software testing …

Researchers have had much recent success with ranking models based on so-called
learned sparse representations generated by transformers. One crucial advantage of this …

Neural information retrieval architectures based on transformers such as BERT are able to
significantly improve system effectiveness over traditional sparse models such as BM25 …

Recent advances in retrieval models based on learned sparse representations generated by
transformers have led us to, once again, consider score-at-a-time query evaluation …

Dual-encoder-based dense retrieval models have become the standard in IR. They employ
large Transformer-based language models, which are notoriously inefficient in terms of …