{"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/hierarchical-dialogue-understanding-with-1","title":"Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention","arxiv_id":"2305.00262","date":"2023-04-29","proceeding":"Tiny Papers @ ICLR 2023 5","authors":["Xiao Liu","Jian Zhang","Heng Zhang","Fuzhao Xue","Yang You"],"abstract":"Compared with standard text, understanding dialogue is more challenging for machines as the dynamic and unexpected semantic changes in each turn. To model such inconsistent semantics, we propose a simple but effective Hierarchical Dialogue Understanding model, HiDialog. Specifically, we first insert multiple special tokens into a dialogue and propose the turn-level attention to learn turn embeddings hierarchically. Then, a heterogeneous graph module is leveraged to polish the learned embeddings. We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification. Results show that our simple approach achieves state-of-the-art performance on all three tasks above. All our source code is publicly available at https://github.com/ShawX825/HiDialog.","url_abs":"https://arxiv.org/abs/2305.00262v1","url_pdf":"https://arxiv.org/pdf/2305.00262v1.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":"hierarchical-dialogue-understanding-with-1","repo_url":"https://github.com/shawx825/hidialog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"dialogue-act-classification","task_name":"Dialogue Act Classification"},{"task_slug":"dialogue-understanding","task_name":"Dialogue Understanding"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialog-relation-extraction-on-dialogre","task":"Dialog Relation Extraction","dataset":"DialogRE","model":"HiDialog","rank_in_archive_order":1,"of":17,"metrics":{"F1 (v2)":"77.1","F1c (v2)":"68.2"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"HiDialog","rank_in_archive_order":12,"of":68,"metrics":{"Weighted-F1":"66.96"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.00262","atlas_url":"https://app.syntology.ai/?focus=2305.00262","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}