Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval

Jang, Kyoungrok; Kang, Junmo; Hong, Giwon; Myaeng, Sung-Hyon; Park, Joohee; Yoon, Taewon; Seo, Hee-Cheol

doi:10.48550/arxiv.2104.07198

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[85] proposed a model called SNRM which uses a neural network to learn a sparse representation of a document and showed that it is able to improve the effectiveness of information retrieval. [86] proposed a model called UHD-BERT which uses a neural network to learn ultra-high-dimensional sparse representations of a document and showed that it is able to improve the effectiveness of full-ranking. [87] proposed a model called BPR which uses a neural network to learn a semantic hash for each passage and showed that it is able to improve the efficiency of open-domain question answering.…”

Section: Discrete Retrieval Methodsmentioning

confidence: 99%

Information Retrieval: Recent Advances and Beyond

Hambarde¹,

Proença²

2023

Preprint

View full text Add to dashboard Cite

In this paper, we provide a detailed overview of the models used for information retrieval in the first and second stages of the typical processing chain. We discuss the current state-of-the-art models, including methods based on terms, semantic retrieval, and neural. Additionally, we delve into the key topics related to the learning process of these models. This way, this survey offers a comprehensive understanding of the field and is of interest for for researchers and practitioners entering/working in the information retrieval domain.

show abstract

Section: Discrete Retrieval Methodsmentioning

confidence: 99%

Information Retrieval: Recent Advances and Beyond

Hambarde¹,

Proença²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Zamani et al [78] proposed a model called SNRM, which uses a neural network to learn a sparse representation of a document and showed that it could improve the effectiveness of information retrieval. Jang et al [79] proposed a model called UHD-BERT, which uses a neural network to learn ultra-high-dimensional sparse representations of a document and showed that it could improve full-ranking effectiveness. Yamada et al [80] proposed a model called BPR, which uses a neural network to learn a semantic hash for each passage and showed that it could improve the efficiency of open-domain question answering.…”

Section: ) Sparse Representation Learningmentioning

confidence: 99%

Information Retrieval: Recent Advances and Beyond

Hambarde

Proença

2023

IEEE Access

View full text Add to dashboard Cite

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. Our discussion encompasses the current state-of-the-art models, covering a wide range of methods and approaches in the field of information retrieval. We delve into the historical development of these models, analyze the key advancements and breakthroughs, and address the challenges and limitations faced by researchers and practitioners in the domain. By offering a comprehensive understanding of the field, this survey is a valuable resource for researchers, practitioners, and newcomers to the information retrieval domain, fostering knowledge growth, innovation, and the development of novel ideas and techniques.INDEX TERMS First-stage retrieval, information retrieval, second-stage retrieval.

show abstract

Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval

Cited by 2 publications

References 19 publications

Information Retrieval: Recent Advances and Beyond

Information Retrieval: Recent Advances and Beyond

Information Retrieval: Recent Advances and Beyond

Contact Info

Product

Resources

About