@inproceedings{f0282c53eefe4c18881c4ae972909507,
title = "Document Set Expansion with Positive-Unlabelled Learning Using Intractable Density Estimation",
abstract = "The Document Set Expansion (DSE) task involves identifying relevant documents from large collections based on a limited set of example documents. Previous research has highlighted Positive and Unlabeled (PU) learning as a promising approach for this task. However, most PU methods rely on the unrealistic assumption of knowing the class prior for positive samples in the collection. To address this limitation, this paper introduces a novel PU learning framework that utilizes intractable density estimation models. Experiments conducted on PubMed and Covid datasets in a transductive setting showcase the effectiveness of the proposed method for DSE. Code is available from https://github.com/Beautifuldog01/Document-set-expansion-puDE.",
keywords = "Density estimation, Document set expansion, Information retrieval, PU learning",
author = "Haiyang Zhang and Qiuyi Chen and Yuanjie Zou and Yushan Pan and Jia Wang and Mark Stevenson",
note = "Publisher Copyright: {\textcopyright} 2024 ELRA Language Resource Association: CC BY-NC 4.0.; Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 ; Conference date: 20-05-2024 Through 25-05-2024",
year = "2024",
language = "English",
series = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "5167--5173",
editor = "Nicoletta Calzolari and Min-Yen Kan and Veronique Hoste and Alessandro Lenci and Sakriani Sakti and Nianwen Xue",
booktitle = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
}