{"url":"/task/short-text-clustering","name":"Short Text Clustering","slug":"short-text-clustering","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":18,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/short-text-clustering-on-stackoverflow","slug":"short-text-clustering-on-stackoverflow","dataset":"Stackoverflow","dataset_url":null,"rows_in_archive":5,"metrics":["Acc","NMI"],"first_row_in_archive_order":{"model":"TCL","paper_title":"Twin Contrastive Learning for Online Clustering","paper_url":"/paper/twin-contrastive-learning-for-online","paper_date":"2022-10-21","arxiv_id":"2210.11680","code_links":[{"title":"Yunfan-Li/Twin-Contrastive-Learning","url":"https://github.com/Yunfan-Li/Twin-Contrastive-Learning"},{"title":"XLearning-SCU/2022-IJCV-TCL","url":"https://github.com/XLearning-SCU/2022-IJCV-TCL"}],"syntology":null}},{"leaderboard":"/sota/short-text-clustering-on-biomedical","slug":"short-text-clustering-on-biomedical","dataset":"Biomedical","dataset_url":null,"rows_in_archive":4,"metrics":["Acc","NMI"],"first_row_in_archive_order":{"model":"TCL","paper_title":"Twin Contrastive Learning for Online Clustering","paper_url":"/paper/twin-contrastive-learning-for-online","paper_date":"2022-10-21","arxiv_id":"2210.11680","code_links":[{"title":"Yunfan-Li/Twin-Contrastive-Learning","url":"https://github.com/Yunfan-Li/Twin-Contrastive-Learning"},{"title":"XLearning-SCU/2022-IJCV-TCL","url":"https://github.com/XLearning-SCU/2022-IJCV-TCL"}],"syntology":null}},{"leaderboard":"/sota/short-text-clustering-on-searchsnippets","slug":"short-text-clustering-on-searchsnippets","dataset":"Searchsnippets","dataset_url":null,"rows_in_archive":4,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/short-text-clustering-on-ag-news","slug":"short-text-clustering-on-ag-news","dataset":"AG News","dataset_url":"/dataset/ag-news","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/short-text-clustering-on-googlenews-s","slug":"short-text-clustering-on-googlenews-s","dataset":"GoogleNews-S","dataset_url":null,"rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/short-text-clustering-on-googlenews-t","slug":"short-text-clustering-on-googlenews-t","dataset":"GoogleNews-T","dataset_url":null,"rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/short-text-clustering-on-googlenews-ts","slug":"short-text-clustering-on-googlenews-ts","dataset":"GoogleNews-TS","dataset_url":null,"rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/short-text-clustering-on-tweet","slug":"short-text-clustering-on-tweet","dataset":"Tweet","dataset_url":null,"rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"SCCL","paper_title":"Supporting Clustering with Contrastive Learning","paper_url":"/paper/supporting-clustering-with-contrastive","paper_date":"2021-03-24","arxiv_id":"2103.12953","code_links":[{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"amazon-research/sccl","url":"https://github.com/amazon-research/sccl"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/ag-news","name":"AG News","full_name":"AG’s News Corpus","num_papers_in_archive":969},{"url":"/dataset/mnad","name":"MNAD","full_name":"Moroccan News Articles Dataset","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/text-clustering","name":"Text Clustering"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":34,"items":[{"url":"/paper/short-text-clustering-via-convolutional","title":"Short Text Clustering via Convolutional Neural Networks","date":"2015-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/twin-contrastive-learning-for-online","title":"Twin Contrastive Learning for Online Clustering","date":"2022-10-21","arxiv_id":"2210.11680","repositories_listed":2,"syntology":null},{"url":"/paper/supporting-clustering-with-contrastive","title":"Supporting Clustering with Contrastive Learning","date":"2021-03-24","arxiv_id":"2103.12953","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/discovering-new-intents-with-deep-aligned","title":"Discovering New Intents with Deep Aligned Clustering","date":"2020-12-16","arxiv_id":"2012.08987","repositories_listed":2,"syntology":null},{"url":"/paper/reliable-pseudo-labeling-via-optimal","title":"Reliable Pseudo-labeling via Optimal Transport with Attention for Short Text Clustering","date":"2025-01-25","arxiv_id":"2501.15194","repositories_listed":1,"syntology":null},{"url":"/paper/discriminative-representation-learning-via","title":"Discriminative Representation learning via Attention-Enhanced Contrastive Learning for Short Text Clustering","date":"2025-01-07","arxiv_id":"2501.03584","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-sentiment-analysis-with-hierarchical","title":"Guiding Sentiment Analysis with Hierarchical Text Clustering: Analyzing the German X/Twitter Discourse on Face Masks in the 2020 COVID-19 Pandemic","date":"2024-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/human-interpretable-clustering-of-short-text","title":"Human-interpretable clustering of short-text using large language models","date":"2024-05-12","arxiv_id":"2405.07278","repositories_listed":1,"syntology":null},{"url":"/paper/robust-representation-learning-with-reliable","title":"Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering","date":"2023-05-23","arxiv_id":"2305.16335","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/ease-entity-aware-contrastive-learning-of-1","title":"EASE: Entity-Aware Contrastive Learning of Sentence Embedding","date":"2022-05-09","arxiv_id":"2205.04260","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/decaf-deep-extreme-classification-with-label","title":"DECAF: Deep Extreme Classification with Label Features","date":"2021-08-01","arxiv_id":"2108.00368","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/eclare-extreme-classification-with-label","title":"ECLARE: Extreme Classification with Label Graph Correlations","date":"2021-07-31","arxiv_id":"2108.00261","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/efficient-sparse-spherical-k-means-for","title":"Efficient Sparse Spherical k-Means for Document Clustering","date":"2021-07-30","arxiv_id":"2108.00895","repositories_listed":1,"syntology":null},{"url":"/paper/intent-mining-from-past-conversations-for","title":"Intent Mining from past conversations for conversational agent","date":"2020-05-22","arxiv_id":"2005.11014","repositories_listed":1,"syntology":null},{"url":"/paper/enhancement-of-short-text-clustering-by","title":"Enhancement of Short Text Clustering by Iterative Classification","date":"2020-01-31","arxiv_id":"2001.11631","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-new-intents-via-constrained-deep","title":"Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement","date":"2019-11-20","arxiv_id":"1911.08891","repositories_listed":1,"syntology":null},{"url":"/paper/a-self-training-approach-for-short-text","title":"A Self-Training Approach for Short Text Clustering","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-taught-convolutional-neural-networks-for","title":"Self-Taught Convolutional Neural Networks for Short Text Clustering","date":"2017-01-01","arxiv_id":"1701.00185","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}