{"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/mintl-minimalist-transfer-learning-for-task","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","arxiv_id":"2009.12005","date":"2020-09-25","proceeding":"EMNLP 2020 11","authors":["Zhaojiang Lin","Andrea Madotto","Genta Indra Winata","Pascale Fung"],"abstract":"In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models, and jointly learn dialogue state tracking and dialogue response generation. Unlike previous approaches, which use a copy mechanism to \"carryover\" the old dialogue states to the new one, we introduce Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minimal generation length. We instantiate our learning framework with two pre-trained backbones: T5 and BART, and evaluate them on MultiWOZ. Extensive experiments demonstrate that: 1) our systems establish new state-of-the-art results on end-to-end response generation, 2) MinTL-based systems are more robust than baseline methods in the low resource setting, and they achieve competitive results with only 20\\% training data, and 3) Lev greatly improves the inference efficiency.","url_abs":"https://arxiv.org/abs/2009.12005v2","url_pdf":"https://arxiv.org/pdf/2009.12005v2.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":"mintl-minimalist-transfer-learning-for-task","repo_url":"https://github.com/zlinao/MinTL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"multi-domain-dialogue-state-tracking","task_name":"Multi-domain Dialogue State Tracking"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.12005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12005"}},"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/zlinao/MinTL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"ebb24f4dc2a81286","entry":"average_distributed_scalar","repo":"zlinao/MinTL","repo_kind":"official","path":"pretraining.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/pretraining.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb24f4dc2a81286"}},{"code_sha256_prefix":"f20c9b1aead27fea","entry":"make_padding_mask","repo":"zlinao/MinTL","repo_kind":"official","path":"BART.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/BART.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f20c9b1aead27fea"}},{"code_sha256_prefix":"e00ccf7847d12b59","entry":"shift_tokens_right","repo":"zlinao/MinTL","repo_kind":"official","path":"BART.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/BART.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e00ccf7847d12b59"}},{"code_sha256_prefix":"5b9d615f09edd9c8","entry":"clean_text","repo":"zlinao/MinTL","repo_kind":"official","path":"damd_multiwoz/clean_dataset.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/damd_multiwoz/clean_dataset.py","link_basis":"first_harvest_node","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":"5b9d615f09edd9c8"}},{"code_sha256_prefix":"4c62f23ce8135bda","entry":"clean_time","repo":"zlinao/MinTL","repo_kind":"official","path":"damd_multiwoz/clean_dataset.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/damd_multiwoz/clean_dataset.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":"4c62f23ce8135bda"}},{"code_sha256_prefix":"c9f6adbecd206460","entry":"invert_mask","repo":"zlinao/MinTL","repo_kind":"official","path":"BART.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/BART.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":"c9f6adbecd206460"}},{"code_sha256_prefix":"82241a05bdff196d","entry":"padOutput","repo":"zlinao/MinTL","repo_kind":"official","path":"pretraining.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/pretraining.py","link_basis":"first_harvest_node","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":"82241a05bdff196d"}},{"code_sha256_prefix":"a9b8c7a10994073f","entry":"puntuation_handler","repo":"zlinao/MinTL","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"a9b8c7a10994073f"}},{"code_sha256_prefix":"01cc69c1c0585dba","entry":"random_spans_noise_mask","repo":"zlinao/MinTL","repo_kind":"official","path":"pretraining.py","file_url":"https://github.com/zlinao/MinTL/blob/HEAD/pretraining.py","link_basis":"first_harvest_node","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":"01cc69c1c0585dba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}