{"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/supporting-clustering-with-contrastive","title":"Supporting Clustering with Contrastive Learning","arxiv_id":"2103.12953","date":"2021-03-24","proceeding":"NAACL 2021 4","authors":["Dejiao Zhang","Feng Nan","Xiaokai Wei","Shangwen Li","Henghui Zhu","Kathleen McKeown","Ramesh Nallapati","Andrew Arnold","Bing Xiang"],"abstract":"Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the beginning of the learning process, which poses a significant challenge for distance-based clustering in achieving good separation between different categories. To this end, we propose Supporting Clustering with Contrastive Learning (SCCL) -- a novel framework to leverage contrastive learning to promote better separation. We assess the performance of SCCL on short text clustering and show that SCCL significantly advances the state-of-the-art results on most benchmark datasets with 3%-11% improvement on Accuracy and 4%-15% improvement on Normalized Mutual Information. Furthermore, our quantitative analysis demonstrates the effectiveness of SCCL in leveraging the strengths of both bottom-up instance discrimination and top-down clustering to achieve better intra-cluster and inter-cluster distances when evaluated with the ground truth cluster labels.","url_abs":"https://arxiv.org/abs/2103.12953v2","url_pdf":"https://arxiv.org/pdf/2103.12953v2.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":"supporting-clustering-with-contrastive","repo_url":"https://github.com/amazon-research/sccl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"supporting-clustering-with-contrastive","repo_url":"https://github.com/makcedward/nlpaug","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"short-text-clustering","task_name":"Short Text Clustering"},{"task_slug":"text-clustering","task_name":"Text Clustering"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"sccl","method_name":"SCCL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"sccl","name":"SCCL","full_name":"Supporting Clustering with Contrastive Learning"}],"results":[{"leaderboard":"/sota/short-text-clustering-on-ag-news","task":"Short Text Clustering","dataset":"AG News","model":"SCCL","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-biomedical","task":"Short Text Clustering","dataset":"Biomedical","model":"SCCL","rank_in_archive_order":2,"of":4,"metrics":{"Acc":"46.2"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-googlenews-s","task":"Short Text Clustering","dataset":"GoogleNews-S","model":"SCCL","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-googlenews-t","task":"Short Text Clustering","dataset":"GoogleNews-T","model":"SCCL","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"75.8"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-googlenews-ts","task":"Short Text Clustering","dataset":"GoogleNews-TS","model":"SCCL","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"89.8"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-searchsnippets","task":"Short Text Clustering","dataset":"Searchsnippets","model":"SCCL","rank_in_archive_order":1,"of":4,"metrics":{"Acc":"85.2"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-stackoverflow","task":"Short Text Clustering","dataset":"Stackoverflow","model":"Deep ECIC","rank_in_archive_order":3,"of":5,"metrics":{"Acc":"SCCL"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-tweet","task":"Short Text Clustering","dataset":"Tweet","model":"SCCL","rank_in_archive_order":1,"of":1,"metrics":{"Acc":"78.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.12953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12953"}},"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/amazon-research/sccl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/makcedward/nlpaug","reach":null}],"summary":{"ran":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":"857857abc8c501ef","entry":"SCCLBert","repo":"amazon-research/sccl","repo_kind":"official","path":"models/Transformers.py","file_url":"https://github.com/amazon-research/sccl/blob/HEAD/models/Transformers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"857857abc8c501ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}