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.
@article{arxiv.1711.06826,
title = {Low-dimensional Embeddings for Interpretable Anchor-based Topic Inference},
author = {Moontae Lee and David Mimno},
journal= {arXiv preprint arXiv:1711.06826},
year = {2017}
}