# Low-dimensional Embeddings for Interpretable Anchor-based Topic Inference

arXiv: https://arxiv.org/abs/1711.06826 · HTML: https://mlsanity.com/paper/1711.06826/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds](https://mlsanity.com/paper/2210.14763/) (2022)
- [On-the-Fly Rectification for Robust Large-Vocabulary Topic Inference](https://mlsanity.com/paper/2111.06580/) (2021)

## Abstract (arXiv)

The anchor words algorithm performs provably efficient topic model inference by finding an approximate convex hull in a high-dimensional word co-occurrence space. However, the existing greedy algorithm often selects poor anchor words, reducing topic quality and interpretability. Rather than finding an approximate convex hull in a high-dimensional space, we propose to find an exact convex hull in a visualizable 2- or 3-dimensional space. Such low-dimensional embeddings both improve topics and clearly show users why the algorithm selects certain words.