{"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/scheduled-multi-task-learning-for-neural-chat","title":"Scheduled Multi-task Learning for Neural Chat Translation","arxiv_id":"2205.03766","date":"2022-05-08","proceeding":"ACL 2022 5","authors":["Yunlong Liang","Fandong Meng","Jinan Xu","Yufeng Chen","Jie zhou"],"abstract":"Neural Chat Translation (NCT) aims to translate conversational text into different languages. Existing methods mainly focus on modeling the bilingual dialogue characteristics (e.g., coherence) to improve chat translation via multi-task learning on small-scale chat translation data. Although the NCT models have achieved impressive success, it is still far from satisfactory due to insufficient chat translation data and simple joint training manners. To address the above issues, we propose a scheduled multi-task learning framework for NCT. Specifically, we devise a three-stage training framework to incorporate the large-scale in-domain chat translation data into training by adding a second pre-training stage between the original pre-training and fine-tuning stages. Further, we investigate where and how to schedule the dialogue-related auxiliary tasks in multiple training stages to effectively enhance the main chat translation task. Extensive experiments in four language directions (English-Chinese and English-German) verify the effectiveness and superiority of the proposed approach. Additionally, we have made the large-scale in-domain paired bilingual dialogue dataset publicly available to the research community.","url_abs":"https://arxiv.org/abs/2205.03766v2","url_pdf":"https://arxiv.org/pdf/2205.03766v2.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":"scheduled-multi-task-learning-for-neural-chat","repo_url":"https://github.com/xl2248/sml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.03766","atlas_url":"https://app.syntology.ai/?focus=2205.03766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03766"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xl2248/sml","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":12},"by_repo_kind":{"official":{"samples":14,"ran":2,"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":"9fb921b5643aea18","entry":"normalize","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/models/rnnsearch_lrp.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/models/rnnsearch_lrp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fb921b5643aea18"}},{"code_sha256_prefix":"b72d57ba22def783","entry":"stabilize","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/models/rnnsearch_lrp.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/models/rnnsearch_lrp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b72d57ba22def783"}},{"code_sha256_prefix":"9755d4d9a4ebe76c","entry":"add_timing_signal","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/attention.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9755d4d9a4ebe76c"}},{"code_sha256_prefix":"a7f5c44fed3d89b6","entry":"bag_of_words_loss","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/losses/losses.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/losses/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7f5c44fed3d89b6"}},{"code_sha256_prefix":"4b23aadce895c6a5","entry":"birnn","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/models/transformer.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/models/transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b23aadce895c6a5"}},{"code_sha256_prefix":"273d5e370a58f518","entry":"combine_heads","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/attention.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"273d5e370a58f518"}},{"code_sha256_prefix":"1358ea72d4fb8741","entry":"gaussian_kld","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/models/contextual_transformer.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/models/contextual_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1358ea72d4fb8741"}},{"code_sha256_prefix":"149a90364d6911d9","entry":"import_params","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/bin/scorer.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/bin/scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"149a90364d6911d9"}},{"code_sha256_prefix":"b299f075318205c0","entry":"layer_norm","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/nn.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b299f075318205c0"}},{"code_sha256_prefix":"ed65fa22e1825000","entry":"linear","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/nn.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed65fa22e1825000"}},{"code_sha256_prefix":"687178b3f006abdc","entry":"maxout","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/nn.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"687178b3f006abdc"}},{"code_sha256_prefix":"b848ccf1e025726b","entry":"merge_parameters","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/bin/scorer.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/bin/scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b848ccf1e025726b"}},{"code_sha256_prefix":"b5dc3b8e8f47d2b8","entry":"sample_gaussian","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/models/contextual_transformer.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/models/contextual_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5dc3b8e8f47d2b8"}},{"code_sha256_prefix":"79a8f2b2454736a1","entry":"split_heads","repo":"xl2248/sml","repo_kind":"official","path":"thumt-sml/thumt/layers/attention.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79a8f2b2454736a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}