Variational Pretraining for Semi-supervised Text Classification · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1906.02242/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTVariational Pretraining for Semi-supervised Text Classification — mentioned by rococodehttps://news.ycombinator.com/item?id=22038795urn:hackerpapers:mention:1906.02242:22038795Mon, 13 Jan 2020 21:25:19 GMT<p>They don&#x27;t use huggingface, but some of the modern approaches for topic modeling use variational auto-encoders, see: Open-SESAME (2017): https://arxiv.org/abs/1706.09528 / https://github.com/swabhs/open-sesame VAMPIRE (2019): https://arxiv.org/abs/1906.02242 / https://github.com/allenai/vampire</p><p><a href="https://hackerpaper.kaipfister.de/p/1906.02242/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL