English

Zero-Shot Multi-Label Topic Inference with Sentence Encoders

Computation and Language 2023-04-18 v1 Information Retrieval

Abstract

Sentence encoders have indeed been shown to achieve superior performances for many downstream text-mining tasks and, thus, claimed to be fairly general. Inspired by this, we performed a detailed study on how to leverage these sentence encoders for the "zero-shot topic inference" task, where the topics are defined/provided by the users in real-time. Extensive experiments on seven different datasets demonstrate that Sentence-BERT demonstrates superior generality compared to other encoders, while Universal Sentence Encoder can be preferred when efficiency is a top priority.

Keywords

Cite

@article{arxiv.2304.07382,
  title  = {Zero-Shot Multi-Label Topic Inference with Sentence Encoders},
  author = {Souvika Sarkar and Dongji Feng and Shubhra Kanti Karmaker Santu},
  journal= {arXiv preprint arXiv:2304.07382},
  year   = {2023}
}
R2 v1 2026-06-28T10:06:35.754Z