{"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/dialogue-act-sequence-labeling-using","title":"Dialogue Act Sequence Labeling using Hierarchical encoder with CRF","arxiv_id":"1709.04250","date":"2017-09-13","proceeding":null,"authors":["Harshit Kumar","Arvind Agarwal","Riddhiman Dasgupta","Sachindra Joshi","Arun Kumar"],"abstract":"Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to\nutterances in a conversation. The problem of associating semantic labels to\nutterances can be treated as a sequence labeling problem. In this work, we\nbuild a hierarchical recurrent neural network using bidirectional LSTM as a\nbase unit and the conditional random field (CRF) as the top layer to classify\neach utterance into its corresponding dialogue act. The hierarchical network\nlearns representations at multiple levels, i.e., word level, utterance level,\nand conversation level. The conversation level representations are input to the\nCRF layer, which takes into account not only all previous utterances but also\ntheir dialogue acts, thus modeling the dependency among both, labels and\nutterances, an important consideration of natural dialogue. We validate our\napproach on two different benchmark data sets, Switchboard and Meeting Recorder\nDialogue Act, and show performance improvement over the state-of-the-art\nmethods by $2.2\\%$ and $4.1\\%$ absolute points, respectively. It is worth\nnoting that the inter-annotator agreement on Switchboard data set is $84\\%$,\nand our method is able to achieve the accuracy of about $79\\%$ despite being\ntrained on the noisy data.","url_abs":"http://arxiv.org/abs/1709.04250v2","url_pdf":"http://arxiv.org/pdf/1709.04250v2.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":"dialogue-act-sequence-labeling-using","repo_url":"https://github.com/ilimugur/short-text-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dialogue-act-sequence-labeling-using","repo_url":"https://github.com/jonas-scholz123/msci-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dialogue-act-sequence-labeling-using","repo_url":"https://github.com/shuyicao/emo-DA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"dialogue-act-classification","task_name":"Dialogue Act Classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-act-classification-on-icsi-meeting","task":"Dialogue Act Classification","dataset":"ICSI Meeting Recorder Dialog Act (MRDA) corpus","model":"Bi-LSTM-CRF","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"90.9"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-act-classification-on-switchboard","task":"Dialogue Act Classification","dataset":"Switchboard corpus","model":"Bi-LSTM-CRF","rank_in_archive_order":7,"of":11,"metrics":{"Accuracy":"79.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.04250","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}