PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zhuoqun, Chen, Xuanang, Lin, Hongyu, Lu, Yaojie, Han, Xianpei, Jiang, Shanshan, Dong, Bin, Sun, Le
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914229203763200
author Li, Zhuoqun
Chen, Xuanang
Lin, Hongyu
Lu, Yaojie
Han, Xianpei
Jiang, Shanshan
Dong, Bin
Sun, Le
author_facet Li, Zhuoqun
Chen, Xuanang
Lin, Hongyu
Lu, Yaojie
Han, Xianpei
Jiang, Shanshan
Dong, Bin
Sun, Le
contents As researchers delve more deeply into their work, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than being limited to coarse-grained topics. However, previous paper search systems are unable to meet these flexible-grained requirements, as previous systems mainly collect paper abstract to construct corpus index, which lacks detailed information to support retrieval by some finer-grained queries. In this work, we propose PaperRegister, which transforms traditional abstract-based index into a hierarchical index tree, thereby supporting queries at flexible granularity. Experiments on paper search tasks across a range of granularity demonstrate that PaperRegister achieves the SOTA performance, and particularly excels in the fine-grained scenarios, highlighting good potential as an effective solution for flexible-grained paper search in real-world applications. https://github.com/Li-Z-Q/PaperRegister.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11116
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
Li, Zhuoqun
Chen, Xuanang
Lin, Hongyu
Lu, Yaojie
Han, Xianpei
Jiang, Shanshan
Dong, Bin
Sun, Le
Information Retrieval
Computation and Language
As researchers delve more deeply into their work, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than being limited to coarse-grained topics. However, previous paper search systems are unable to meet these flexible-grained requirements, as previous systems mainly collect paper abstract to construct corpus index, which lacks detailed information to support retrieval by some finer-grained queries. In this work, we propose PaperRegister, which transforms traditional abstract-based index into a hierarchical index tree, thereby supporting queries at flexible granularity. Experiments on paper search tasks across a range of granularity demonstrate that PaperRegister achieves the SOTA performance, and particularly excels in the fine-grained scenarios, highlighting good potential as an effective solution for flexible-grained paper search in real-world applications. https://github.com/Li-Z-Q/PaperRegister.
title PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2508.11116