{"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/conversational-analysis-using-utterance-level","title":"Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks","arxiv_id":"1805.06242","date":"2018-05-16","proceeding":null,"authors":["Chandrakant Bothe","Sven Magg","Cornelius Weber","Stefan Wermter"],"abstract":"Recent approaches for dialogue act recognition have shown that context from\npreceding utterances is important to classify the subsequent one. It was shown\nthat the performance improves rapidly when the context is taken into account.\nWe propose an utterance-level attention-based bidirectional recurrent neural\nnetwork (Utt-Att-BiRNN) model to analyze the importance of preceding utterances\nto classify the current one. In our setup, the BiRNN is given the input set of\ncurrent and preceding utterances. Our model outperforms previous models that\nuse only preceding utterances as context on the used corpus. Another\ncontribution of the article is to discover the amount of information in each\nutterance to classify the subsequent one and to show that context-based\nlearning not only improves the performance but also achieves higher confidence\nin the classification. We use character- and word-level features to represent\nthe utterances. The results are presented for character and word feature\nrepresentations and as an ensemble model of both representations. We found that\nwhen classifying short utterances, the closest preceding utterances contributes\nto a higher degree.","url_abs":"http://arxiv.org/abs/1805.06242v2","url_pdf":"http://arxiv.org/pdf/1805.06242v2.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":"conversational-analysis-using-utterance-level","repo_url":"https://github.com/bothe/dialogue-act-recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dialog-act-classification","task_name":"Dialog Act Classification"},{"task_slug":"dialogue-act-classification","task_name":"Dialogue Act Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-act-classification-on-switchboard","task":"Dialogue Act Classification","dataset":"Switchboard corpus","model":"Utt-Att-BiRNN","rank_in_archive_order":9,"of":11,"metrics":{"Accuracy":"77.42"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}