{"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/improving-neural-topic-models-using-knowledge","title":"Improving Neural Topic Models using Knowledge Distillation","arxiv_id":"2010.02377","date":"2020-10-05","proceeding":"EMNLP 2020 11","authors":["Alexander Hoyle","Pranav Goel","Philip Resnik"],"abstract":"Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our modular method can be straightforwardly applied with any neural topic model to improve topic quality, which we demonstrate using two models having disparate architectures, obtaining state-of-the-art topic coherence. We show that our adaptable framework not only improves performance in the aggregate over all estimated topics, as is commonly reported, but also in head-to-head comparisons of aligned topics.","url_abs":"https://arxiv.org/abs/2010.02377v1","url_pdf":"https://arxiv.org/pdf/2010.02377v1.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":"improving-neural-topic-models-using-knowledge","repo_url":"https://github.com/ahoho/kd-topic-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"mxnet","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.02377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02377"}},"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":"deterministic:regex_extraction","url":"https://github.com/awslabs/w-lda","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ahoho/kd-topic-models","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/aws/aws-parallelcluster","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"found_in_text":{"samples":4,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"ac0981baa5b5018d","entry":"get_docs_from_index","repo":"awslabs/w-lda","repo_kind":"found_in_text","path":"npmi_calc.py","file_url":"https://github.com/awslabs/w-lda/blob/HEAD/npmi_calc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac0981baa5b5018d"}},{"code_sha256_prefix":"95b0415763a46f97","entry":"get_pmi","repo":"awslabs/w-lda","repo_kind":"found_in_text","path":"npmi_calc.py","file_url":"https://github.com/awslabs/w-lda/blob/HEAD/npmi_calc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"95b0415763a46f97"}},{"code_sha256_prefix":"ba7c64a369a90618","entry":"intersecting_docs","repo":"awslabs/w-lda","repo_kind":"found_in_text","path":"npmi_calc.py","file_url":"https://github.com/awslabs/w-lda/blob/HEAD/npmi_calc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba7c64a369a90618"}},{"code_sha256_prefix":"d019e10d6cf916a9","entry":"reverse_dict","repo":"awslabs/w-lda","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/awslabs/w-lda/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d019e10d6cf916a9"}},{"code_sha256_prefix":"37cc697b1ec7b864","entry":"torchScholar","repo":"ahoho/kd-topic-models","repo_kind":"official","path":"scholar/scholar.py","file_url":"https://github.com/ahoho/kd-topic-models/blob/HEAD/scholar/scholar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37cc697b1ec7b864"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}