{"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/multi-task-pre-training-for-plug-and-play","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","arxiv_id":"2109.14739","date":"2021-09-29","proceeding":"ACL 2022 5","authors":["Yixuan Su","Lei Shu","Elman Mansimov","Arshit Gupta","Deng Cai","Yi-An Lai","Yi Zhang"],"abstract":"Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead to error accumulation across different sub-tasks and greater data annotation overhead. In this study, we present PPTOD, a unified plug-and-play model for task-oriented dialogue. In addition, we introduce a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora. We extensively test our model on three benchmark TOD tasks, including end-to-end dialogue modelling, dialogue state tracking, and intent classification. Experimental results show that PPTOD achieves new state of the art on all evaluated tasks in both high-resource and low-resource scenarios. Furthermore, comparisons against previous SOTA methods show that the responses generated by PPTOD are more factually correct and semantically coherent as judged by human annotators.","url_abs":"https://arxiv.org/abs/2109.14739v2","url_pdf":"https://arxiv.org/pdf/2109.14739v2.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":"multi-task-pre-training-for-plug-and-play","repo_url":"https://github.com/awslabs/pptod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-task-pre-training-for-plug-and-play","repo_url":"https://github.com/sogang-isds/TOATOD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"end-to-end-dialogue-modelling","task_name":"End-To-End Dialogue Modelling"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.14739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14739"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sogang-isds/TOATOD","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awslabs/pptod","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"157e7d21e425e71b","entry":"batch_generate","repo":"awslabs/pptod","repo_kind":"official","path":"DST/inference_utlis.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/inference_utlis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"157e7d21e425e71b"}},{"code_sha256_prefix":"ea3e5b726884db6d","entry":"clean_text","repo":"awslabs/pptod","repo_kind":"official","path":"E2E_TOD/clean_dataset.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/E2E_TOD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea3e5b726884db6d"}},{"code_sha256_prefix":"4c62f23ce8135bda","entry":"clean_time","repo":"awslabs/pptod","repo_kind":"official","path":"E2E_TOD/clean_dataset.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/E2E_TOD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c62f23ce8135bda"}},{"code_sha256_prefix":"ddc6b154895626c0","entry":"erase_error","repo":"awslabs/pptod","repo_kind":"official","path":"DST/inference_utlis.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/inference_utlis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ddc6b154895626c0"}},{"code_sha256_prefix":"0ee004932e081b43","entry":"fix_mismatch_jason","repo":"awslabs/pptod","repo_kind":"official","path":"DST/dst.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/dst.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ee004932e081b43"}},{"code_sha256_prefix":"bb26485d8e62dade","entry":"get_checkpoint_name","repo":"awslabs/pptod","repo_kind":"official","path":"E2E_TOD/inference_pptod.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/E2E_TOD/inference_pptod.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb26485d8e62dade"}},{"code_sha256_prefix":"213ac11a76f93ae8","entry":"ignore_none","repo":"awslabs/pptod","repo_kind":"official","path":"DST/dst.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/dst.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"213ac11a76f93ae8"}},{"code_sha256_prefix":"7f5a7dafc8e4429c","entry":"my_clean_text","repo":"awslabs/pptod","repo_kind":"official","path":"E2E_TOD/clean_dataset.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/E2E_TOD/clean_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f5a7dafc8e4429c"}},{"code_sha256_prefix":"5d59ec0edc0482ac","entry":"restore_text","repo":"awslabs/pptod","repo_kind":"official","path":"DST/inference_utlis.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/inference_utlis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d59ec0edc0482ac"}},{"code_sha256_prefix":"79bc40569254969f","entry":"zip_result","repo":"awslabs/pptod","repo_kind":"official","path":"DST/inference.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79bc40569254969f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}