{"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-dynamic-memory-network-for-dialogue","title":"Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training","arxiv_id":"1811.05021","date":"2018-11-12","proceeding":null,"authors":["Yao Wan","Wenqiang Yan","Jianwei Gao","Zhou Zhao","Jian Wu","Philip S. Yu"],"abstract":"Dialogue Act (DA) classification is a challenging problem in dialogue\ninterpretation, which aims to attach semantic labels to utterances and\ncharacterize the speaker's intention. Currently, many existing approaches\nformulate the DA classification problem ranging from multi-classification to\nstructured prediction, which suffer from two limitations: a) these methods are\neither handcrafted feature-based or have limited memories. b) adversarial\nexamples can't be correctly classified by traditional training methods. To\naddress these issues, in this paper we first cast the problem into a question\nand answering problem and proposed an improved dynamic memory networks with\nhierarchical pyramidal utterance encoder. Moreover, we apply adversarial\ntraining to train our proposed model. We evaluate our model on two public\ndatasets, i.e., Switchboard dialogue act corpus and the MapTask corpus.\nExtensive experiments show that our proposed model is not only robust, but also\nachieves better performance when compared with some state-of-the-art baselines.","url_abs":"http://arxiv.org/abs/1811.05021v1","url_pdf":"http://arxiv.org/pdf/1811.05021v1.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":"classification-1","task_name":"Classification"},{"task_slug":"dialogue-act-classification","task_name":"Dialogue Act Classification"},{"task_slug":"dialogue-interpretation","task_name":"Dialogue Interpretation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-act-classification-on-switchboard","task":"Dialogue Act Classification","dataset":"Switchboard corpus","model":"ALDMN","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"81.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}