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 …
Large language models for information retrieval: A survey
As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …
search engines, have integrated themselves into our daily lives. These systems also serve …
[图书][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 …
Document expansion by query prediction
One technique to improve the retrieval effectiveness of a search engine is to expand
documents with terms that are related or representative of the documents' content. From the …
documents with terms that are related or representative of the documents' content. From the …
An introduction to neural information retrieval
B Mitra, N Craswell - Foundations and Trends® in Information …, 2018 - nowpublishers.com
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to
rank search results in response to a query. Traditional learning to rank models employ …
rank search results in response to a query. Traditional learning to rank models employ …
Rankvicuna: Zero-shot listwise document reranking with open-source large language models
Researchers have successfully applied large language models (LLMs) such as ChatGPT to
reranking in an information retrieval context, but to date, such work has mostly been built on …
reranking in an information retrieval context, but to date, such work has mostly been built on …
Pre-training methods in information retrieval
The core of information retrieval (IR) is to identify relevant information from large-scale
resources and return it as a ranked list to respond to user's information need. In recent years …
resources and return it as a ranked list to respond to user's information need. In recent years …
Generation-augmented retrieval for open-domain question answering
We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions,
which augments a query through text generation of heuristically discovered relevant …
which augments a query through text generation of heuristically discovered relevant …
Anserini: Reproducible ranking baselines using Lucene
This work tackles the perennial problem of reproducible baselines in information retrieval
research, focusing on bag-of-words ranking models. Although academic information …
research, focusing on bag-of-words ranking models. Although academic information …
Simple applications of BERT for ad hoc document retrieval
Following recent successes in applying BERT to question answering, we explore simple
applications to ad hoc document retrieval. This required confronting the challenge posed by …
applications to ad hoc document retrieval. This required confronting the challenge posed by …