{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-sinkhorn-topic-model","title":"Neural Topic Model via Optimal Transport","arxiv_id":"2008.13537","date":"2020-08-12","proceeding":"ICLR 2021 1","authors":["He Zhao","Dinh Phung","Viet Huynh","Trung Le","Wray Buntine"],"abstract":"Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis. However, it is usually hard for existing NTMs to achieve good document representation and coherent/diverse topics at the same time. Moreover, they often degrade their performance severely on short documents. The requirement of reparameterisation could also comprise their training quality and model flexibility. To address these shortcomings, we present a new neural topic model via the theory of optimal transport (OT). Specifically, we propose to learn the topic distribution of a document by directly minimising its OT distance to the document's word distributions. Importantly, the cost matrix of the OT distance models the weights between topics and words, which is constructed by the distances between topics and words in an embedding space. Our proposed model can be trained efficiently with a differentiable loss. Extensive experiments show that our framework significantly outperforms the state-of-the-art NTMs on discovering more coherent and diverse topics and deriving better document representations for both regular and short texts.","url_abs":"https://arxiv.org/abs/2008.13537v3","url_pdf":"https://arxiv.org/pdf/2008.13537v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-sinkhorn-topic-model","repo_url":"https://github.com/ethanhezhao/NeuralSinkhornTopicModel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/topic-models-on-20newsgroups","task":"Topic Models","dataset":"20NewsGroups","model":"NSTM","rank_in_archive_order":5,"of":6,"metrics":{"C_v":"0.38"},"uses_additional_data":false},{"leaderboard":"/sota/topic-models-on-ag-news","task":"Topic Models","dataset":"AG News","model":"NSTM","rank_in_archive_order":5,"of":6,"metrics":{"C_v":"0.37","NPMI":"-0.04"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13537"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ethanhezhao/NeuralSinkhornTopicModel","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1e2fce38febef428","entry":"sinkhorn_tf","repo":"ethanhezhao/NeuralSinkhornTopicModel","repo_kind":"official","path":"auto_diff_sinkhorn.py","file_url":"https://github.com/ethanhezhao/NeuralSinkhornTopicModel/blob/HEAD/auto_diff_sinkhorn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e2fce38febef428"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}