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 …

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 …

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 …

A vital step towards the widespread adoption of neural retrieval models is their resource
efficiency throughout the training, indexing and query workflows. The neural IR community …

In neural Information Retrieval, ongoing research is directed towards improving the first
retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using …

Abstract Knowledge-intensive language tasks require NLP systems to both provide the
correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive …

Conducting text retrieval in a dense learned representation space has many intriguing
advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires …

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances
in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for …

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 …

Ranking has always been one of the top concerns in information retrieval researches. For
decades, the lexical matching signal has dominated the ad-hoc retrieval process, but solely …