Semantic models for the first-stage retrieval: A comprehensive review
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 …
where the first-stage retrieval is to return a subset of candidate documents and latter stages …
Information retrieval: recent advances and beyond
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 …
utilized in the first and second stages of the typical information retrieval processing chain …
Colbertv2: Effective and efficient retrieval via lightweight late interaction
Neural information retrieval (IR) has greatly advanced search and other knowledge-
intensive language tasks. While many neural IR methods encode queries and documents …
intensive language tasks. While many neural IR methods encode queries and documents …
Dense text retrieval based on pretrained language models: A survey
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 …
required to return relevant information resources to user's queries in natural language. From …
Rocketqav2: A joint training method for dense passage retrieval and passage re-ranking
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 …
two key procedures in finding and ranking relevant information. Since both the two …
[LIBRO][B] Pretrained transformers for text ranking: Bert and beyond
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 …
response to a query. Although the most common formulation of text ranking is search …
Optimizing dense retrieval model training with hard negatives
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 …
decades, the lexical matching signal has dominated the ad-hoc retrieval process, but solely …
Pretrained transformers for text ranking: BERT and beyond
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 …
response to a query. Although the most common formulation of text ranking is search …
Adversarial retriever-ranker for dense text retrieval
Current dense text retrieval models face two typical challenges. First, they adopt a siamese
dual-encoder architecture to encode queries and documents independently for fast indexing …
dual-encoder architecture to encode queries and documents independently for fast indexing …
SAILER: structure-aware pre-trained language model for legal case retrieval
Legal case retrieval, which aims to find relevant cases for a query case, plays a core role in
the intelligent legal system. Despite the success that pre-training has achieved in ad-hoc …
the intelligent legal system. Despite the success that pre-training has achieved in ad-hoc …