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 …

Neural information retrieval (IR) has greatly advanced search and other knowledge-
intensive language tasks. While many neural IR methods encode queries and documents …

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM)
for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily …

In various natural language processing tasks, passage retrieval and passage re-ranking are
two key procedures in finding and ranking relevant information. Since both the two …

In open-domain question answering, dense passage retrieval has become a new paradigm
to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is …

Pretrained language models such as BERT have been shown to be exceptionally effective
for text ranking. However, there are limited studies on how to leverage more powerful …

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 …

Pre-trained Transformer language models (LM) have become go-to text representation
encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences …

Classical information retrieval systems such as BM25 rely on exact lexical match and carry
out search efficiently with inverted list index. Recent neural IR models shifts towards soft …

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 …