Density-Aware Prototypical Network for Few-Shot Relation Classification

Jianfeng Wu, Mengting Hu, Yike Wu, Bingzhe Wu, Yalan Xie, Mingming Liu, Renhong Cheng

Submission Type: Regular Long Paper

Submission Track: Information Extraction

Keywords: Few-shot relation classification, None-of-the-above challenge, Density estimation

TL;DR: To address the none-of-the-above (NOTA) challenge in few-shot relation classification, we introduce NCA loss and NOTA loss to optimize the instance distribution, and design a novel density estimation method to detect NOTA.

Abstract: In recent years, few-shot relation classification has evoked many research interests. Yet a more challenging problem, i.e. none-of-the-above (NOTA), is under-explored. Existing works mainly regard NOTA as an extra class and treat it the same as known relations. However, such a solution ignores the overall instance distribution, where NOTA instances are actually outliers and distributed unnaturally compared with known ones. In this paper, we propose a density-aware prototypical network (D-Proto) to treat various instances distinctly. Specifically, we design unique training objectives to separate known instances and isolate NOTA instances, respectively. This produces an ideal instance distribution, where known instances are dense yet NOTAs have a small density. Moreover, we propose a NOTA detection module to further enlarge the density of known samples, and discriminate NOTA and known samples accurately. Experimental results demonstrate that the proposed method outperforms strong baselines with robustness towards various NOTA rates. The code will be made public after the paper is accepted.

Submission Number: 982