# Zero-Shot Multi-Label Topic Inference with Sentence Encoders

arXiv: https://arxiv.org/abs/2304.07382 · HTML: https://mlsanity.com/paper/2304.07382/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 67 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey](https://mlsanity.com/paper/1711.04305/) (2017)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [Zero-shot Text Classification With Generative Language Models](https://mlsanity.com/paper/1912.10165/) (2019)
- [Zero-shot User Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1809.00385/) (2018)
- [BioSentVec: creating sentence embeddings for biomedical texts](https://mlsanity.com/paper/1810.09302/) (2018)
- [Generative and Discriminative Text Classification with Recurrent Neural Networks](https://mlsanity.com/paper/1703.01898/) (2017)
- [Evaluation of sentence embeddings in downstream and linguistic probing tasks](https://mlsanity.com/paper/1806.06259/) (2018)
- [Integrating Semantic Knowledge to Tackle Zero-shot Text Classification](https://mlsanity.com/paper/1903.12626/) (2019)
- [Train Once, Test Anywhere: Zero-Shot Learning for Text Classification](https://mlsanity.com/paper/1712.05972/) (2017)
- [Zero-Shot Audio Classification via Semantic Embeddings](https://mlsanity.com/paper/2011.12133/) (2020)
- [Multi-label Dataless Text Classification with Topic Modeling](https://mlsanity.com/paper/1711.01563/) (2017)
- [Zero-shot Relation Classification from Side Information](https://mlsanity.com/paper/2011.07126/) (2020)
- [Towards Automated Sexual Violence Report Tracking](https://mlsanity.com/paper/1911.06961/) (2019)
- [Dual-View Distilled BERT for Sentence Embedding](https://mlsanity.com/paper/2104.08675/) (2021)
- [Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages](https://mlsanity.com/paper/1810.08740/) (2018)
- [Covid-Transformer: Detecting COVID-19 Trending Topics on Twitter Using Universal Sentence Encoder](https://mlsanity.com/paper/2009.03947/) (2020)
- [A Transfer Learning Approach for Dialogue Act Classification of GitHub Issue Comments](https://mlsanity.com/paper/2011.04867/) (2020)

## Built on by (most cited first, 6 of 6)

- [Fundamental Limits of Perfect Concept Erasure](https://mlsanity.com/paper/2503.20098/) (2025)
- [Large Language Models for Healthcare Text Classification: A Systematic Review](https://mlsanity.com/paper/2503.01159/) (2025)
- [Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders](https://mlsanity.com/paper/2503.02993/) (2025)
- [QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification](https://mlsanity.com/paper/2502.14189/) (2025)
- [Leveraging Large Language Models for Fuzzy String Matching in Political Science](https://mlsanity.com/paper/2403.18218/) (2024)
- [Population-level measures of perceived food access reveal barriers beyond geographic proximity](https://mlsanity.com/paper/2609.12132/) (2026)

## Abstract (arXiv)

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.