はてなブックマーク

Perplexity To Evaluate Topic Models May 15th, 2013 🦖 This post was published in 2013 and is most likely outdated. The most common way to evaluate a probabilistic model is to measure the log-likelihood of a held-out test set. This is usually done by splitting the dataset into two parts: one for training, the other for testing. For LDA, a test set is a collection of unseen documents $\boldsymbol w_