{"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/revisiting-distributional-correspondence","title":"Revisiting Distributional Correspondence Indexing: A Python Reimplementation and New Experiments","arxiv_id":"1810.09311","date":"2018-10-19","proceeding":null,"authors":["Alejandro Moreo","Andrea Esuli","Fabrizio Sebastiani"],"abstract":"This paper introduces PyDCI, a new implementation of Distributional\nCorrespondence Indexing (DCI) written in Python. DCI is a transfer learning\nmethod for cross-domain and cross-lingual text classification for which we had\nprovided an implementation (here called JaDCI) built on top of JaTeCS, a Java\nframework for text classification. PyDCI is a stand-alone version of DCI that\nexploits scikit-learn and the SciPy stack. We here report on new experiments\nthat we have carried out in order to test PyDCI, and in which we use as\nbaselines new high-performing methods that have appeared after DCI was\noriginally proposed. These experiments show that, thanks to a few subtle ways\nin which we have improved DCI, PyDCI outperforms both JaDCI and the\nabove-mentioned high-performing methods, and delivers the best known results on\nthe two popular benchmarks on which we had tested DCI, i.e.,\nMultiDomainSentiment (a.k.a. MDS -- for cross-domain adaptation) and\nWebis-CLS-10 (for cross-lingual adaptation). PyDCI, together with the code\nallowing to replicate our experiments, is available at\nhttps://github.com/AlexMoreo/pydci .","url_abs":"http://arxiv.org/abs/1810.09311v1","url_pdf":"http://arxiv.org/pdf/1810.09311v1.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":"revisiting-distributional-correspondence","repo_url":"https://github.com/AlexMoreo/pydci","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-multi-domain-sentiment","task":"Sentiment Analysis","dataset":"Multi-Domain Sentiment Dataset","model":"Distributional Correspondence Indexing","rank_in_archive_order":2,"of":6,"metrics":{"Average":"83.30","Books":"81.4","DVD":"81.00","Electronics":"85,06","Kitchen":"85.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}