# Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding

arXiv: https://arxiv.org/abs/2007.09536 · HTML: https://mlsanity.com/paper/2007.09536/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 22 of 22)

- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations](https://mlsanity.com/paper/2202.04582/) (2022)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [Corpus-based Open-Domain Event Type Induction](https://mlsanity.com/paper/2109.03322/) (2021)
- [HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding](https://mlsanity.com/paper/2210.10625/) (2022)
- [Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts](https://mlsanity.com/paper/2212.06002/) (2022)
- [Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy](https://mlsanity.com/paper/2403.04160/) (2024)
- [TopicNet: Semantic Graph-Guided Topic Discovery](https://mlsanity.com/paper/2110.14286/) (2021)
- [Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation](https://mlsanity.com/paper/2206.13746/) (2022)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation](https://mlsanity.com/paper/2211.01981/) (2022)
- [Fast and Multi-aspect Mining of Complex Time-stamped Event Streams](https://mlsanity.com/paper/2303.03789/) (2023)
- [Knowledge-Aware Bayesian Deep Topic Model](https://mlsanity.com/paper/2209.14228/) (2022)
- [Self-supervised Topic Taxonomy Discovery in the Box Embedding Space](https://mlsanity.com/paper/2408.15050/) (2024)
- [Disentangled Contrastive Learning for Learning Robust Textual Representations](https://mlsanity.com/paper/2104.04907/) (2021)
- [Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings](https://mlsanity.com/paper/2506.00277/) (2025)
- [Fine-Grained Opinion Summarization with Minimal Supervision](https://mlsanity.com/paper/2110.08845/) (2021)
- [Out-of-Category Document Identification Using Target-Category Names as Weak Supervision](https://mlsanity.com/paper/2111.12796/) (2021)
- [Seeded Hierarchical Clustering for Expert-Crafted Taxonomies](https://mlsanity.com/paper/2205.11602/) (2022)
- [HyHTM: Hyperbolic Geometry based Hierarchical Topic Models](https://mlsanity.com/paper/2305.09258/) (2023)
- [Generalised Spherical Text Embedding](https://mlsanity.com/paper/2211.16801/) (2022)
- [Performance of Data Augmentation Methods for Brazilian Portuguese Text Classification](https://mlsanity.com/paper/2304.02785/) (2023)

## Abstract (arXiv)

Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora. To account for potential hierarchical topic structures, hierarchical topic models generalize flat topic models by incorporating latent topic hierarchies into their generative modeling process. However, due to their purely unsupervised nature, the learned topic hierarchy often deviates from users' particular needs or interests. To guide the hierarchical topic discovery process with minimal user supervision, we propose a new task, Hierarchical Topic Mining, which takes a category tree described by category names only, and aims to mine a set of representative terms for each category from a text corpus to help a user comprehend his/her interested topics. We develop a novel joint tree and text embedding method along with a principled optimization procedure that allows simultaneous modeling of the category tree structure and the corpus generative process in the spherical space for effective category-representative term discovery. Our comprehensive experiments show that our model, named JoSH, mines a high-quality set of hierarchical topics with high efficiency and benefits weakly-supervised hierarchical text classification tasks.