{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-clustering","name":"Text Clustering","slug":"text-clustering","description_markdown":"Grouping a set of texts in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). (Source: Adapted from Wikipedia)","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":123,"papers_with_code":38,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":5,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-clustering-on-mteb","slug":"text-clustering-on-mteb","dataset":"MTEB","dataset_url":"/dataset/mteb","rows_in_archive":31,"metrics":["V-Measure"],"first_row_in_archive_order":{"model":"ST5-XXL","paper_title":"MTEB: Massive Text Embedding Benchmark","paper_url":"/paper/mteb-massive-text-embedding-benchmark","paper_date":"2022-10-13","arxiv_id":"2210.07316","code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}],"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}},"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/text-clustering-on-20-newsgroups","slug":"text-clustering-on-20-newsgroups","dataset":"20 Newsgroups","dataset_url":"/dataset/20-newsgroups","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"G-BAT","paper_title":"Neural Topic Modeling with Bidirectional Adversarial Training","paper_url":"/paper/neural-topic-modeling-with-bidirectional","paper_date":"2020-04-26","arxiv_id":"2004.12331","code_links":[{"title":"zll17/Neural_Topic_Models","url":"https://github.com/zll17/Neural_Topic_Models"}],"syntology":null}},{"leaderboard":"/sota/text-clustering-on-urdu-news-headlines","slug":"text-clustering-on-urdu-news-headlines","dataset":"Urdu News Headlines Dataset","dataset_url":"/dataset/urdu-news-headlines-dataset","rows_in_archive":1,"metrics":["Related Headlines"],"first_row_in_archive_order":{"model":"Vector Space Model","paper_title":"Clustering Urdu News Using Headlines","paper_url":"/paper/clustering-urdu-news-using-headlines","paper_date":"2015-09-27","arxiv_id":null,"code_links":[{"title":"SyedMuhammadFaheem/Urdu-News-Clustering","url":"https://github.com/SyedMuhammadFaheem/Urdu-News-Clustering"}],"syntology":null}}],"datasets":[{"url":"/dataset/mteb","name":"MTEB","full_name":"Massive Text Embedding Benchmark","num_papers_in_archive":155},{"url":"/dataset/20-newsgroups","name":"20 Newsgroups","full_name":"","num_papers_in_archive":27},{"url":"/dataset/covid-19-twitter-chatter-dataset","name":"COVID-19 Twitter Chatter Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/italian-crime-news","name":"DICE: a Dataset of Italian Crime Event news","full_name":"from Gazzetta di Modena [2011-2021]","num_papers_in_archive":3},{"url":"/dataset/urdu-news-headlines-dataset","name":"Urdu News Headlines Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/hierarchical-text-clustering","name":"Hierarchical Text Clustering"},{"url":"/task/open-intent-discovery","name":"Open Intent Discovery"},{"url":"/task/short-text-clustering","name":"Short Text Clustering"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":123,"of_with_code":38,"tagged_in_all":123,"counts":{"archive_papers_tagged":123,"with_a_code_link":38,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":123,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/mteb-massive-text-embedding-benchmark","slug":"mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","arxiv_id":"2210.07316","repositories_listed":5,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}},"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/short-text-clustering-via-convolutional","slug":"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/a-proposition-level-clustering-approach-for","slug":"a-proposition-level-clustering-approach-for","title":"Proposition-Level Clustering for Multi-Document Summarization","date":"2021-12-16","arxiv_id":"2112.08770","repositories_listed":2,"syntology":null},{"url":"/paper/supporting-clustering-with-contrastive","slug":"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_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/supporting-clustering-with-contrastive#ran","syntology_url":"https://syntology.ai/paper/2103.12953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12953"}},"official":{"repos":["amazon-research/sccl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-new-intents-with-deep-aligned","slug":"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/dissimilarity-mixture-autoencoder-for-deep","slug":"dissimilarity-mixture-autoencoder-for-deep","title":"Dissimilarity Mixture Autoencoder for Deep Clustering","date":"2020-06-15","arxiv_id":"2006.08177","repositories_listed":2,"syntology":null},{"url":"/paper/cse-sfp-enabling-unsupervised-sentence","slug":"cse-sfp-enabling-unsupervised-sentence","title":"CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass","date":"2025-05-01","arxiv_id":"2505.00389","repositories_listed":1,"syntology":null},{"url":"/paper/reliable-pseudo-labeling-via-optimal","slug":"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","slug":"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/text-clustering-as-classification-with-llms","slug":"text-clustering-as-classification-with-llms","title":"Text Clustering as Classification with LLMs","date":"2024-09-30","arxiv_id":"2410.00927","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/text-clustering-as-classification-with-llms#ran","syntology_url":"https://syntology.ai/paper/2410.00927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00927"}},"official":{"repos":["ecnu-text-computing/text-clustering-via-llm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/neurcam-interpretable-neural-clustering-via","slug":"neurcam-interpretable-neural-clustering-via","title":"NeurCAM: Interpretable Neural Clustering via Additive Models","date":"2024-08-23","arxiv_id":"2408.13361","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-sentiment-analysis-with-hierarchical","slug":"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","slug":"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/more-discriminative-sentence-embeddings-via","slug":"more-discriminative-sentence-embeddings-via","title":"More Discriminative Sentence Embeddings via Semantic Graph Smoothing","date":"2024-02-20","arxiv_id":"2402.12890","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-enable-few-shot","slug":"large-language-models-enable-few-shot","title":"Large Language Models Enable Few-Shot Clustering","date":"2023-07-02","arxiv_id":"2307.00524","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-enable-few-shot#ran","syntology_url":"https://syntology.ai/paper/2307.00524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00524"}},"official":{"repos":["viswavi/few-shot-clustering"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clusterllm-large-language-models-as-a-guide","slug":"clusterllm-large-language-models-as-a-guide","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","date":"2023-05-24","arxiv_id":"2305.14871","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clusterllm-large-language-models-as-a-guide#ran","syntology_url":"https://syntology.ai/paper/2305.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14871"}},"official":{"repos":["zhang-yu-wei/clusterllm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-representation-learning-with-reliable","slug":"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_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/robust-representation-learning-with-reliable#ran","syntology_url":"https://syntology.ai/paper/2305.16335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16335"}},"official":{"repos":["hmllmh/rstc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/influence-of-various-text-embeddings-on","slug":"influence-of-various-text-embeddings-on","title":"Influence of various text embeddings on clustering performance in NLP","date":"2023-05-04","arxiv_id":"2305.03144","repositories_listed":1,"syntology":null},{"url":"/paper/deeplens-interactive-out-of-distribution-data","slug":"deeplens-interactive-out-of-distribution-data","title":"DeepLens: Interactive Out-of-distribution Data Detection in NLP Models","date":"2023-03-02","arxiv_id":"2303.01577","repositories_listed":1,"syntology":null},{"url":"/paper/very-large-language-model-as-a-unified","slug":"very-large-language-model-as-a-unified","title":"Very Large Language Model as a Unified Methodology of Text Mining","date":"2022-12-19","arxiv_id":"2212.09271","repositories_listed":1,"syntology":null},{"url":"/paper/training-effective-neural-sentence-encoders","slug":"training-effective-neural-sentence-encoders","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","date":"2022-07-26","arxiv_id":"2207.12759","repositories_listed":1,"syntology":null},{"url":"/paper/clustering-similar-amendments-at-the-italian","slug":"clustering-similar-amendments-at-the-italian","title":"Clustering Similar Amendments at the Italian Senate","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ease-entity-aware-contrastive-learning-of-1","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ease-entity-aware-contrastive-learning-of-1#ran","syntology_url":"https://syntology.ai/paper/2205.04260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.04260"}},"official":{"repos":["studio-ousia/ease"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/subspace-co-clustering-with-two-way-graph","slug":"subspace-co-clustering-with-two-way-graph","title":"Subspace Co-clustering with Two-Way Graph Convolution","date":"2022-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/proposition-level-clustering-for-multi","slug":"proposition-level-clustering-for-multi","title":"Proposition-Level Clustering for Multi-Document Summarization","date":"2022-01-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/task-oriented-clustering-for-dialogues","slug":"task-oriented-clustering-for-dialogues","title":"Task-Oriented Clustering for Dialogues","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/translation-transformers-rediscover-inherent","slug":"translation-transformers-rediscover-inherent","title":"Translation Transformers Rediscover Inherent Data Domains","date":"2021-09-16","arxiv_id":"2109.07864","repositories_listed":1,"syntology":null},{"url":"/paper/learn-the-big-picture-representation-learning","slug":"learn-the-big-picture-representation-learning","title":"Learn The Big Picture: Representation Learning for Clustering","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/efficient-sparse-spherical-k-means-for","slug":"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/comstreamclust-a-communicative-text","slug":"comstreamclust-a-communicative-text","title":"ComStreamClust: a communicative multi-agent approach to text clustering in streaming data","date":"2020-10-11","arxiv_id":"2010.05349","repositories_listed":1,"syntology":null},{"url":"/paper/neural-topic-modeling-with-bidirectional","slug":"neural-topic-modeling-with-bidirectional","title":"Neural Topic Modeling with Bidirectional Adversarial Training","date":"2020-04-26","arxiv_id":"2004.12331","repositories_listed":1,"syntology":null},{"url":"/paper/enhancement-of-short-text-clustering-by","slug":"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","slug":"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","slug":"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/on-the-use-of-arxiv-as-a-dataset","slug":"on-the-use-of-arxiv-as-a-dataset","title":"On the Use of ArXiv as a Dataset","date":"2019-04-30","arxiv_id":"1905.00075","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-the-use-of-arxiv-as-a-dataset#ran","syntology_url":"https://syntology.ai/paper/1905.00075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00075"}},"official":{"repos":["mattbierbaum/arxiv-public-datasets"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/elki-a-large-open-source-library-for-data","slug":"elki-a-large-open-source-library-for-data","title":"ELKI: A large open-source library for data analysis - ELKI Release 0.7.5 \"Heidelberg\"","date":"2019-02-10","arxiv_id":"1902.03616","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elki-a-large-open-source-library-for-data#ran","syntology_url":"https://syntology.ai/paper/1902.03616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.03616"}},"official":{"repos":["elki-project/elki"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-taught-convolutional-neural-networks-for","slug":"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},{"url":"/paper/clustering-urdu-news-using-headlines","slug":"clustering-urdu-news-using-headlines","title":"Clustering Urdu News Using Headlines","date":"2015-09-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"moving-past-single-metrics-exploring-short","title":"Moving Past Single Metrics: Exploring Short-Text Clustering Across Multiple Resolutions","date":"2025-02-24","arxiv_id":"2502.17020","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-text-analytics-graph-neural-network","title":"Advanced Text Analytics -- Graph Neural Network for Fake News Detection in Social Media","date":"2025-02-22","arxiv_id":"2502.16157","repositories_listed":0,"syntology":null},{"url":null,"slug":"k-llmmeans-scalable-stable-and-interpretable","title":"k-LLMmeans: Scalable, Stable, and Interpretable Text Clustering via LLM-based Centroids","date":"2025-02-12","arxiv_id":"2502.09667","repositories_listed":0,"syntology":null},{"url":null,"slug":"lita-an-efficient-llm-assisted-iterative","title":"LITA: An Efficient LLM-assisted Iterative Topic Augmentation Framework","date":"2024-12-17","arxiv_id":"2412.12459","repositories_listed":0,"syntology":null},{"url":null,"slug":"dial-in-llm-human-aligned-dialogue-intent","title":"Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues","date":"2024-12-12","arxiv_id":"2412.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-mixtures-of-unigram-models-for","title":"Hierarchical mixtures of Unigram models for short text clustering: The role of Beta-Liouville priors","date":"2024-10-29","arxiv_id":"2410.21862","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-subspace-for-text","title":"Contrastive Learning Subspace for Text Clustering","date":"2024-08-26","arxiv_id":"2408.14119","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-sentence-embeddings-from","title":"Extracting Sentence Embeddings from Pretrained Transformer Models","date":"2024-08-15","arxiv_id":"2408.08073","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-and-explanatory-image-and-text","title":"An Efficient and Explanatory Image and Text Clustering System with Multimodal Autoencoder Architecture","date":"2024-08-14","arxiv_id":"2408.07791","repositories_listed":0,"syntology":null},{"url":null,"slug":"zerodl-zero-shot-distribution-learning-for","title":"ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models","date":"2024-06-19","arxiv_id":"2406.13342","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-clustering-using-large-language","title":"Context-Aware Clustering using Large Language Models","date":"2024-05-02","arxiv_id":"2405.00988","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-clustering-applied-to-data-augmentation","title":"Text clustering applied to data augmentation in legal contexts","date":"2024-04-08","arxiv_id":"2404.08683","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-clustering-with-llm-embeddings","title":"Text Clustering with Large Language Model Embeddings","date":"2024-03-22","arxiv_id":"2403.15112","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-teaching-learning-based","title":"An enhanced Teaching-Learning-Based Optimization (TLBO) with Grey Wolf Optimizer (GWO) for text feature selection and clustering","date":"2024-02-19","arxiv_id":"2402.11839","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-construction-of-multi-faceted-user","title":"Automatic Construction of Multi-faceted User Profiles using Text Clustering and its Application to Expert Recommendation and Filtering Problems","date":"2024-01-19","arxiv_id":"2401.10634","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-hierarchical-text-clustering","title":"Incremental hierarchical text clustering methods: a review","date":"2023-12-12","arxiv_id":"2312.07769","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-for-short-text-clustering","title":"Federated Learning for Short Text Clustering","date":"2023-11-23","arxiv_id":"2312.07556","repositories_listed":0,"syntology":null},{"url":null,"slug":"elastic-deep-autoencoder-for-text-embedding","title":"Elastic deep autoencoder for text embedding clustering by an improved graph regularization","date":"2023-09-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lacos-bloom-low-rank-adaptation-with","title":"LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM","date":"2023-05-10","arxiv_id":"2305.06404","repositories_listed":0,"syntology":null},{"url":null,"slug":"ceil-a-general-classification-enhanced","title":"CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering","date":"2023-04-20","arxiv_id":"2304.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptersoup-weight-averaging-to-improve","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","date":"2023-02-14","arxiv_id":"2302.07027","repositories_listed":0,"syntology":null},{"url":null,"slug":"clustop-an-unsupervised-and-integrated-text","title":"ClusTop: An unsupervised and integrated text clustering and topic extraction framework","date":"2023-01-03","arxiv_id":"2301.00818","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-deep-embedded-clustering-via","title":"Improving Deep Embedded Clustering via Learning Cluster-level Representations","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clustering-induced-generative-incomplete","title":"Clustering-Induced Generative Incomplete Image-Text Clustering (CIGIT-C)","date":"2022-09-28","arxiv_id":"2209.13763","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-pattern-no-recognition-a-survey-about","title":"No Pattern, No Recognition: a Survey about Reproducibility and Distortion Issues of Text Clustering and Topic Modeling","date":"2022-08-02","arxiv_id":"2208.01712","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-text-block-detection-towards-scene","title":"Contextual Text Block Detection towards Scene Text Understanding","date":"2022-07-26","arxiv_id":"2207.12955","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-responsible-ai-for-financial","title":"Towards Responsible AI for Financial Transactions","date":"2022-06-06","arxiv_id":"2206.02419","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-topic-modeling-with-deep-mutual","title":"Neural Topic Modeling with Deep Mutual Information Estimation","date":"2022-03-12","arxiv_id":"2203.06298","repositories_listed":0,"syntology":null},{"url":null,"slug":"ease-entity-aware-contrastive-learning-of","title":"EASE: Entity-Aware Contrastive Learning of Sentence Embedding","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-clustering-with-contrastive","title":"Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents","date":"2022-01-07","arxiv_id":"2201.07604","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-short-text","title":"Representation Learning for Short Text Clustering","date":"2021-09-21","arxiv_id":"2109.09894","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-multisource-feature-fusion-for-the","title":"Hybrid Multisource Feature Fusion for the Text Clustering","date":"2021-08-24","arxiv_id":"2108.10926","repositories_listed":0,"syntology":null},{"url":null,"slug":"localize-group-and-select-boosting-text-vqa","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","date":"2021-08-20","arxiv_id":"2108.08965","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-and-clustering-with","title":"Text Classification and Clustering with Annealing Soft Nearest Neighbor Loss","date":"2021-07-23","arxiv_id":"2107.14597","repositories_listed":0,"syntology":null},{"url":"/paper/deep-clustering-with-measure-propagation","slug":"deep-clustering-with-measure-propagation","title":"Deep Clustering with Measure Propagation","date":"2021-04-18","arxiv_id":"2104.08967","repositories_listed":0,"syntology":null},{"url":null,"slug":"cluster-analysis-of-online-mental-health","title":"Cluster Analysis of Online Mental Health Discourse using Topic-Infused Deep Contextualized Representations","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amharic-text-clustering-using-encyclopedic","title":"Amharic Text Clustering Using Encyclopedic Knowledge with Neural Word Embedding","date":"2021-03-31","arxiv_id":"2105.00809","repositories_listed":0,"syntology":null},{"url":"/paper/short-text-clustering-with-transformers","slug":"short-text-clustering-with-transformers","title":"Short Text Clustering with Transformers","date":"2021-01-31","arxiv_id":"2102.00541","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-survey-of-unsupervised-text","title":"An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data","date":"2020-12-07","arxiv_id":"2012.03468","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-fine-tuning-for-text-clustering","title":"Unsupervised Fine-tuning for Text Clustering","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-text-classification-by-jointly-1","title":"Neural Text Classification by Jointly Learning to Cluster and Align","date":"2020-11-24","arxiv_id":"2011.12184","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-document-clustering-based-on","title":"Self-supervised Document Clustering Based on BERT with Data Augment","date":"2020-11-17","arxiv_id":"2011.08523","repositories_listed":0,"syntology":null},{"url":null,"slug":"unification-of-hdp-and-lda-models-for-optimal","title":"Unification of HDP and LDA Models for Optimal Topic Clustering of Subject Specific Question Banks","date":"2020-10-04","arxiv_id":"2011.01035","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-online-semantic-enhanced-dirichlet-model","title":"An Online Semantic-enhanced Dirichlet Model for Short Text Stream Clustering","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-for-azerbaijani-language","title":"Text Classification for Azerbaijani Language Using Machine Learning and Embedding","date":"2019-12-26","arxiv_id":"1912.13362","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-representation-learning-with","title":"Attentive Representation Learning with Adversarial Training for Short Text Clustering","date":"2019-12-08","arxiv_id":"1912.03720","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-mining-using-nonnegative-matrix","title":"Text Mining using Nonnegative Matrix Factorization and Latent Semantic Analysis","date":"2019-11-12","arxiv_id":"1911.04705","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-neural-network-framework-for","title":"An end-to-end Neural Network Framework for Text Clustering","date":"2019-03-22","arxiv_id":"1903.09424","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-clustering-on-comparative-texts-via","title":"Mutual Clustering on Comparative Texts via Heterogeneous Information Networks","date":"2019-03-09","arxiv_id":"1903.03762","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-embedding-induced-text-clustering","title":"Sequential Embedding Induced Text Clustering, a Non-parametric Bayesian Approach","date":"2018-11-29","arxiv_id":"1811.12500","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-thematic-similarity-metric-from","title":"Learning Thematic Similarity Metric from Article Sections Using Triplet Networks","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-short-text-responses-clustering","title":"Multilingual Short Text Responses Clustering for Mobile Educational Activities: a Preliminary Exploration","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-text-similarity-measure-that","title":"A Graph-based Text Similarity Measure That Employs Named Entity Information","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-clustering-based-on-content-and","title":"Hybrid Clustering based on Content and Connection Structure using Joint Nonnegative Matrix Factorization","date":"2017-03-28","arxiv_id":"1703.09646","repositories_listed":0,"syntology":null},{"url":null,"slug":"character-aware-neural-networks-for-arabic","title":"Character-Aware Neural Networks for Arabic Named Entity Recognition for Social Media","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disco-a-system-leveraging-semantic-search-in","title":"DISCO: A System Leveraging Semantic Search in Document Review","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"accounting-ngrams-and-multi-word-terms-can","title":"Accounting ngrams and multi-word terms can improve topic models","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-creativity-and-cluster-tightness","title":"Effects of Creativity and Cluster Tightness on Short Text Clustering Performance","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-clustering-for-short-text-via","title":"Semi-supervised Clustering for Short Text via Deep Representation Learning","date":"2016-02-22","arxiv_id":"1602.06797","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-bayesian-modelling-approach","title":"An Unsupervised Bayesian Modelling Approach for Storyline Detection on News Articles","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tsdpmm-incorporating-prior-topic-knowledge","title":"TSDPMM: Incorporating Prior Topic Knowledge into Dirichlet Process Mixture Models for Text Clustering","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"news-clustering-approach-based-on-discourse","title":"News clustering approach based on discourse text structure","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":9,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/text-clustering-on-mteb","since_archive":"/sota/text-clustering-on-mteb#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/text-clustering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/text-clustering/papers/2","json":"/task/text-clustering/papers/2.json","rows":23},{"order":"ran","page":1,"of":1,"url":"/task/text-clustering/papers/ran/1","json":"/task/text-clustering/papers/ran/1.json","rows":9}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"fc88d312bfbd0fb8be80a095883906df0870a7e28e281a18bf69135e555cf34e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}