中文
相关论文

相关论文: How does Feedback Signal Quality Impact Effectiven…

200 篇论文

Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform traditional bag-of-words rerankers. However, it is unclear how to…

信息检索 · 计算机科学 2022-07-04 Hang Li , Ahmed Mourad , Shengyao Zhuang , Bevan Koopman , Guido Zuccon

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

信息检索 · 计算机科学 2024-01-23 Suchana Datta , Debasis Ganguly , Sean MacAvaney , Derek Greene

Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-k passages from the first round of retrieval to perform a second round of retrieval aiming to improve search effectiveness. A recent research direction has been the…

信息检索 · 计算机科学 2023-03-22 Hang Li , Shengyao Zhuang , Ahmed Mourad , Xueguang Ma , Jimmy Lin , Guido Zuccon

Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansion models using text…

信息检索 · 计算机科学 2023-05-15 Iain Mackie , Shubham Chatterjee , Jeffrey Dalton

Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the…

信息检索 · 计算机科学 2026-03-12 Nour Jedidi , Jimmy Lin

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document…

信息检索 · 计算机科学 2018-11-01 Canjia Li , Yingfei Sun , Ben He , Le Wang , Kai Hui , Andrew Yates , Le Sun , Jungang Xu

The Relevance Feedback (RF) process relies on accurate and real-time relevance estimation of feedback documents to improve retrieval performance. Since collecting explicit relevance annotations imposes an extra burden on the user, extensive…

人工智能 · 计算机科学 2023-12-12 Ziyi Ye , Xiaohui Xie , Qingyao Ai , Yiqun Liu , Zhihong Wang , Weihang Su , Min Zhang

Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents.…

信息检索 · 计算机科学 2022-04-26 Yunchang Zhu , Liang Pang , Yanyan Lan , Huawei Shen , Xueqi Cheng

Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little…

信息检索 · 计算机科学 2018-12-24 Keping Bi , Qingyao Ai , W. Bruce Croft

Current query expansion models use pseudo-relevance feedback to improve first-pass retrieval effectiveness; however, this fails when the initial results are not relevant. Instead of building a language model from retrieved results, we…

信息检索 · 计算机科学 2023-04-27 Iain Mackie , Shubham Chatterjee , Jeffrey Dalton

Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process. However, the application of pseudo…

信息检索 · 计算机科学 2023-08-22 Xueru Wen , Xiaoyang Chen , Xuanang Chen , Ben He , Le Sun

Pseudo relevance feedback (PRF) automatically performs query expansion based on top-retrieved documents to better represent the user's information need so as to improve the search results. Previous PRF methods mainly select expansion terms…

信息检索 · 计算机科学 2021-11-17 Handong Ma , Jiawei Hou , Chenxu Zhu , Weinan Zhang , Ruiming Tang , Jincai Lai , Jieming Zhu , Xiuqiang He , Yong Yu

Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and…

信息检索 · 计算机科学 2021-09-01 HongChien Yu , Chenyan Xiong , Jamie Callan

As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval. Previously, an effective…

信息检索 · 计算机科学 2019-06-11 Keping Bi , Qingyao Ai , W. Bruce Croft

Scaling dense retrievers to larger large language model (LLM) backbones has been a dominant strategy for improving their retrieval effectiveness. However, this has substantial cost implications: larger backbones require more expensive…

信息检索 · 计算机科学 2025-06-09 Hang Li , Xiao Wang , Bevan Koopman , Guido Zuccon

Query rewriting is a fundamental technique in information retrieval (IR). It typically employs the retrieval result as relevance feedback to refine the query and thereby addresses the vocabulary mismatch between user queries and relevant…

信息检索 · 计算机科学 2025-10-30 Yiteng Tu , Weihang Su , Yujia Zhou , Yiqun Liu , Fen Lin , Qin Liu , Qingyao Ai

Information-seeking conversation systems are increasingly popular in real-world applications, especially for e-commerce companies. To retrieve appropriate responses for users, it is necessary to compute the matching degrees between…

计算与语言 · 计算机科学 2022-11-03 Haojie Pan , Cen Chen , Chengyu Wang , Minghui Qiu , Liu Yang , Feng Ji , Jun Huang

Most research on pseudo relevance feedback (PRF) has been done in vector space and probabilistic retrieval models. This paper shows that Transformer-based rerankers can also benefit from the extra context that PRF provides. It presents PGT,…

信息检索 · 计算机科学 2021-01-21 HongChien Yu , Zhuyun Dai , Jamie Callan

Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval. Recently, with the rapid advance of deep learning techniques, neural text generation has achieved promising…

信息检索 · 计算机科学 2021-08-16 Minghui Huang , Dong Wang , Shuang Liu , Meizhen Ding

Retrieval-enhanced methods have become a primary approach in fact verification (FV); it requires reasoning over multiple retrieved pieces of evidence to verify the integrity of a claim. To retrieve evidence, existing work often employs…

信息检索 · 计算机科学 2025-10-21 Hengran Zhang , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng
‹ 上一页 1 2 3 10 下一页 ›