HOTTER: Hierarchical Optimal Topic Transport with Explanatory Context Representations

1 code implementation • Findings (EMNLP) 2021 • Sabine Wehnert, Christian Scheel, Simona Szakács-Behling, Maret Nieländer, Patrick Mielke, Ernesto William De Luca

In this paper we propose an extension to a specific emerging hybrid document distance metric which combines topic models and word embeddings: the Hierarchical Optimal Topic Transport (HOTT).

Information Retrieval Language Modelling +3