{"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/scdv-sparse-composite-document-vectors-using","title":"SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations","arxiv_id":"1612.06778","date":"2016-12-20","proceeding":"EMNLP 2017 9","authors":["Dheeraj Mekala","Vivek Gupta","Bhargavi Paranjape","Harish Karnick"],"abstract":"We present a feature vector formation technique for documents - Sparse\nComposite Document Vector (SCDV) - which overcomes several shortcomings of the\ncurrent distributional paragraph vector representations that are widely used\nfor text representation. In SCDV, word embedding's are clustered to capture\nmultiple semantic contexts in which words occur. They are then chained together\nto form document topic-vectors that can express complex, multi-topic documents.\nThrough extensive experiments on multi-class and multi-label classification\ntasks, we outperform the previous state-of-the-art method, NTSG (Liu et al.,\n2015a). We also show that SCDV embedding's perform well on heterogeneous tasks\nlike Topic Coherence, context-sensitive Learning and Information Retrieval.\nMoreover, we achieve significant reduction in training and prediction times\ncompared to other representation methods. SCDV achieves best of both worlds -\nbetter performance with lower time and space complexity.","url_abs":"http://arxiv.org/abs/1612.06778v3","url_pdf":"http://arxiv.org/pdf/1612.06778v3.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":"scdv-sparse-composite-document-vectors-using","repo_url":"https://github.com/dheeraj7596/SCDV","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"scdv-sparse-composite-document-vectors-using","repo_url":"https://github.com/MartinMachac/TextClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"scdv-sparse-composite-document-vectors-using","repo_url":"https://github.com/haradai1262/scdv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"scdv-sparse-composite-document-vectors-using","repo_url":"https://github.com/nyk510/scdv-python","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.06778","atlas_url":"https://app.syntology.ai/?focus=1612.06778","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}