March 23, 2024
Author(s)
Zongxia Li, Andrew Mao, Jordan Boyd-Graber, Daniel Stephens, Emily Walpole, Alden A. Dima, Juan Fung
Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models