{"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/incomplete-utterance-rewriting-as-semantic","title":"Incomplete Utterance Rewriting as Semantic Segmentation","arxiv_id":"2009.13166","date":"2020-09-28","proceeding":"EMNLP 2020 11","authors":["Qian Liu","Bei Chen","Jian-Guang Lou","Bin Zhou","Dongmei Zhang"],"abstract":"Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead of generating from scratch, such a formulation introduces edit operations and shapes the problem as prediction of a word-level edit matrix. Benefiting from being able to capture both local and global information, our approach achieves state-of-the-art performance on several public datasets. Furthermore, our approach is four times faster than the standard approach in inference.","url_abs":"https://arxiv.org/abs/2009.13166v1","url_pdf":"https://arxiv.org/pdf/2009.13166v1.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":"incomplete-utterance-rewriting-as-semantic","repo_url":"https://github.com/microsoft/ContextualSP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"context-query-reformulation","task_name":"Context Query Reformulation"},{"task_slug":"dialogue-rewriting","task_name":"Dialogue Rewriting"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-rewriting-on-multi-rewrite","task":"Dialogue Rewriting","dataset":"Multi-Rewrite","model":"RUN+BERT","rank_in_archive_order":1,"of":3,"metrics":{"Rewriting F3":"47.7"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-rewriting-on-rewrite","task":"Dialogue Rewriting","dataset":"Rewrite","model":"RUN+BERT","rank_in_archive_order":1,"of":1,"metrics":{"ROUGE-L":"93.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.13166","atlas_url":"https://app.syntology.ai/?focus=2009.13166","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}