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 …

Ever since the Turing Test was proposed in the 1950s, humans have explored the mastering
of language intelligence by machine. Language is essentially a complex, intricate system of …

In this paper, we present a new embedding model, called M3-Embedding, which is
distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity. It …

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a
wide range of tasks. The model is trained in a contrastive manner with weak supervision …

This paper introduces a simple yet effective query expansion approach, denoted as
query2doc, to improve both sparse and dense retrieval systems. The proposed method first …

Text retrieval is a long-standing research topic on information seeking, where a system is
required to return relevant information resources to user's queries in natural language. From …

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 …

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

Lexical matching remains the de facto evaluation method for open-domain question
answering (QA). Unfortunately, lexical matching fails completely when a plausible candidate …

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 …