[HTML][HTML] Information retrieval meets large language models: a strategic report from chinese ir community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond
traditional search to meet diverse user information needs. Recently, Large Language …
traditional search to meet diverse user information needs. Recently, Large Language …
Strubert: Structure-aware bert for table search and matching
A table is composed of data values that are organized in rows and columns providing
implicit structural information. A table is usually accompanied by secondary information such …
implicit structural information. A table is usually accompanied by secondary information such …
Feb4rag: Evaluating federated search in the context of retrieval augmented generation
Federated search systems aggregate results from multiple search engines, selecting
appropriate sources to enhance result quality and align with user intent. With the increasing …
appropriate sources to enhance result quality and align with user intent. With the increasing …
Deep learning model for covid-19 sentiment analysis on twitter
S Contreras Hernández, MP Tzili Cruz… - New Generation …, 2023 - Springer
The COVID-19 pandemic impacted the mood of the people, and this was evident on social
networks. These common user publications are a source of information to measure the …
networks. These common user publications are a source of information to measure the …
Dame: Domain adaptation for matching entities
Entity matching (EM) identifies data records that refer to the same real-world entity. Despite
the effort in the past years to improve the performance in EM, the existing methods still …
the effort in the past years to improve the performance in EM, the existing methods still …
Learning to co-embed queries and documents
Y Wu, B Lu, L Tian, S Liang - Electronics, 2022 - mdpi.com
Learning to Rank (L2R) methods that utilize machine learning techniques to solve the
ranking problems have been widely studied in the field of information retrieval. Existing …
ranking problems have been widely studied in the field of information retrieval. Existing …
Topics in contextualised attention embeddings
M Talebpour, A García Seco de Herrera… - European Conference on …, 2023 - Springer
Contextualised word vectors obtained via pre-trained language models encode a variety of
knowledge that has already been exploited in applications. Complementary to these …
knowledge that has already been exploited in applications. Complementary to these …
Alloprof: a new french question-answer education dataset and its use in an information retrieval case study
A Lefebvre-Brossard, S Gazaille… - arXiv preprint arXiv …, 2023 - arxiv.org
Teachers and students are increasingly relying on online learning resources to supplement
the ones provided in school. This increase in the breadth and depth of available resources is …
the ones provided in school. This increase in the breadth and depth of available resources is …
Heterogeneous hypergraph learning for literature retrieval based on citation intents
K Shi, K Liu, X He - Scientometrics, 2024 - Springer
Literature retrieval helps scientists find previous work that is relative to their own research or
even get new research ideas. However, the discrepancy between retrieval results and the …
even get new research ideas. However, the discrepancy between retrieval results and the …
VILE: Block-Aware Visual Enhanced Document Retrieval
Document retrieval has always been a crucial problem in Web search. Recent works
leverage pre-trained language models to represent documents in dense vectors. However …
leverage pre-trained language models to represent documents in dense vectors. However …