{"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/self-taught-convolutional-neural-networks-for","title":"Self-Taught Convolutional Neural Networks for Short Text Clustering","arxiv_id":"1701.00185","date":"2017-01-01","proceeding":null,"authors":["Jiaming Xu","Peng Wang","Suncong Zheng","Guanhua Tian","Jun Zhao","Bo Xu"],"abstract":"Short text clustering is a challenging problem due to its sparseness of text\nrepresentation. Here we propose a flexible Self-Taught Convolutional neural\nnetwork framework for Short Text Clustering (dubbed STC^2), which can flexibly\nand successfully incorporate more useful semantic features and learn non-biased\ndeep text representation in an unsupervised manner. In our framework, the\noriginal raw text features are firstly embedded into compact binary codes by\nusing one existing unsupervised dimensionality reduction methods. Then, word\nembeddings are explored and fed into convolutional neural networks to learn\ndeep feature representations, meanwhile the output units are used to fit the\npre-trained binary codes in the training process. Finally, we get the optimal\nclusters by employing K-means to cluster the learned representations. Extensive\nexperimental results demonstrate that the proposed framework is effective,\nflexible and outperform several popular clustering methods when tested on three\npublic short text datasets.","url_abs":"http://arxiv.org/abs/1701.00185v1","url_pdf":"http://arxiv.org/pdf/1701.00185v1.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":"self-taught-convolutional-neural-networks-for","repo_url":"https://github.com/jacoxu/STC2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"short-text-clustering","task_name":"Short Text Clustering"},{"task_slug":"text-clustering","task_name":"Text Clustering"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/short-text-clustering-on-biomedical","task":"Short Text Clustering","dataset":"Biomedical","model":"STC2-LE","rank_in_archive_order":3,"of":4,"metrics":{"Acc":"43.62"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-biomedical","task":"Short Text Clustering","dataset":"Biomedical","model":"STC2-LPI","rank_in_archive_order":4,"of":4,"metrics":{"Acc":"43"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-searchsnippets","task":"Short Text Clustering","dataset":"Searchsnippets","model":"STC2-LE","rank_in_archive_order":3,"of":4,"metrics":{"Acc":"77.09"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-searchsnippets","task":"Short Text Clustering","dataset":"Searchsnippets","model":"STC2-LPI","rank_in_archive_order":4,"of":4,"metrics":{"Acc":"77.01"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-stackoverflow","task":"Short Text Clustering","dataset":"Stackoverflow","model":"Deep ECIC","rank_in_archive_order":4,"of":5,"metrics":{"Acc":"STC2-LE"},"uses_additional_data":false},{"leaderboard":"/sota/short-text-clustering-on-stackoverflow","task":"Short Text Clustering","dataset":"Stackoverflow","model":"Deep ECIC","rank_in_archive_order":5,"of":5,"metrics":{"Acc":"STC2-LPI"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1701.00185","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}