{"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/improved-deep-learning-baselines-for-ubuntu","title":"Improved Deep Learning Baselines for Ubuntu Corpus Dialogs","arxiv_id":"1510.03753","date":"2015-10-13","proceeding":null,"authors":["Rudolf Kadlec","Martin Schmid","Jan Kleindienst"],"abstract":"This paper presents results of our experiments for the next utterance ranking\non the Ubuntu Dialog Corpus -- the largest publicly available multi-turn dialog\ncorpus. First, we use an in-house implementation of previously reported models\nto do an independent evaluation using the same data. Second, we evaluate the\nperformances of various LSTMs, Bi-LSTMs and CNNs on the dataset. Third, we\ncreate an ensemble by averaging predictions of multiple models. The ensemble\nfurther improves the performance and it achieves a state-of-the-art result for\nthe next utterance ranking on this dataset. Finally, we discuss our future\nplans using this corpus.","url_abs":"http://arxiv.org/abs/1510.03753v2","url_pdf":"http://arxiv.org/pdf/1510.03753v2.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":[],"tasks":[{"task_slug":"conversational-response-selection","task_name":"Conversational Response Selection"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conversational-response-selection-on-ubuntu-1","task":"Conversational Response Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"Dual-BiLSTM","rank_in_archive_order":24,"of":25,"metrics":{"R10@1":"0.630","R10@2":"0.780","R10@5":"0.944","R2@1":"0.895"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1510.03753","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}