A Appendix

A.1 List of Neural T opic Modeling Works used in our Meta-Analysis Corpus statistics are in Table 7. Document processing - We do not process documents with fewer than 25 whitespace-separated tokens. Following processing (e.g., stopword removal), we remove documents with fewer than The vocabulary is created from the training data. Stop-words are retained if they are contained within detected noun entities (e.g., "The United States of America" united_states_of_america). - We filter out tokens with two or fewer characters. Standard rules-of-thumb for vocabulary pruning, like removing terms that appear in fewer than 0.5% of To keep vocabulary sizes roughly consistent across datasets, we set the minimum document-frequency for terms as a (power) function of the total corpus size. We use gensim ( ˇ Reh u ˇ rek and Sojka, 2010) as a Python wrapper for running Mallet.