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

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 finegrained scenarios, highlighting good potential as an effective solution for flexible-grained paper search in real-world applications. https: //github.com/Li-Z-Q/PaperRegister . Experiment Evaluating qa tasks get conclusions … Motivation Model parametric are not enough solving ... Implementation Train the BART as LM, BERT as text enc. to … Abstract Non-parametric and explicit memory … Operation Jointly minimizing neg marginal log likelihood, fix doc encoder … Module Use Bert-large 330M and a …