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 …

Existing neural information retrieval (IR) models have often been studied in homogeneous
and narrow settings, which has considerably limited insights into their out-of-distribution …

In this paper, we demonstrate that information retrieval can be accomplished with a single
Transformer, in which all information about the corpus is encoded in the parameters of the …

It has been shown that dual encoders trained on one domain often fail to generalize to other
domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual …

We provide the first exploration of sentence embeddings from text-to-text transformers (T5).
Sentence embeddings are broadly useful for language processing tasks. While T5 achieves …

Much recent research on information retrieval has focused on how to transfer from one task
(typically with abundant supervised data) to various other tasks where supervision is limited …

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 …

As a new paradigm in information retrieval, generative retrieval directly generates a ranked
list of document identifiers (docids) for a given query using generative language models …

We introduce two pre-trained retrieval focused multilingual sentence encoding models,
respectively based on the Transformer and CNN model architectures. The models embed …