The dataset Wikitext-103 and the word embedding files could not be uploaded due to system limitations. For word embedding, it can be downloaded from Glove website (https://nlp.stanford.edu/projects/glove/). The raw dataset for Wikitext-103, which you can download on https://www.salesforce.com/products/einstein/ai-research/the-wikitext-dependency-language-modeling-dataset/ We use the same preprocessing steps as described in Nan et al. (2019) to obtain the vocabulary of Wikitext-103. Nan, F.; Ding, R.; Nallapati, R.; and Xiang, B. 2019. Topic Modeling with Wasserstein Autoencoders. In ACL, 6345–6381.