{"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/revisiting-self-training-for-few-shot","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","arxiv_id":"2110.01256","date":"2021-10-04","proceeding":"EMNLP 2021 11","authors":["Yiming Chen","Yan Zhang","Chen Zhang","Grandee Lee","Ran Cheng","Haizhou Li"],"abstract":"As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM. Given two views of a text sample via weak and strong augmentation techniques, SFLM generates a pseudo label on the weakly augmented version. Then, the model predicts the same pseudo label when fine-tuned with the strongly augmented version. This simple approach is shown to outperform other state-of-the-art supervised and semi-supervised counterparts on six sentence classification and six sentence-pair classification benchmarking tasks. In addition, SFLM only relies on a few in-domain unlabeled data. We conduct a comprehensive analysis to demonstrate the robustness of our proposed approach under various settings, including augmentation techniques, model scale, and few-shot knowledge transfer across tasks.","url_abs":"https://arxiv.org/abs/2110.01256v1","url_pdf":"https://arxiv.org/pdf/2110.01256v1.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":"revisiting-self-training-for-few-shot","repo_url":"https://github.com/matthewcym/sflm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"sentence-pair-classification","task_name":"Sentence-Pair Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.01256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01256"}},"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":"deterministic:regex_extraction","url":"https://github.com/timoschick/pet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/matthewcym/sflm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":3,"unverified":7},"by_repo_kind":{"official":{"samples":6,"ran":4,"repositories":1},"found_in_text":{"samples":5,"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":"e448786d5ff1875a","entry":"default_dev_objective","repo":"matthewcym/sflm","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/trainer.py","link_basis":"harvester_set","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":"e448786d5ff1875a"}},{"code_sha256_prefix":"e768e25ca95f70cd","entry":"input_example_to_string","repo":"matthewcym/sflm","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e768e25ca95f70cd"}},{"code_sha256_prefix":"fbef70dc7c700501","entry":"input_example_to_tuple","repo":"matthewcym/sflm","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbef70dc7c700501"}},{"code_sha256_prefix":"b62076c5483738dc","entry":"text_classification_metrics","repo":"matthewcym/sflm","repo_kind":"official","path":"src/processors.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/processors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b62076c5483738dc"}},{"code_sha256_prefix":"8ce575c2247ba48a","entry":"eq_div","repo":"timoschick/pet","repo_kind":"found_in_text","path":"pet/utils.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/pet/utils.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":"8ce575c2247ba48a"}},{"code_sha256_prefix":"a40f233e44e61f6e","entry":"filter_words","repo":"timoschick/pet","repo_kind":"found_in_text","path":"petal.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/petal.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":"a40f233e44e61f6e"}},{"code_sha256_prefix":"999a29a2aa943ed5","entry":"get_logger","repo":"timoschick/pet","repo_kind":"found_in_text","path":"log.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/log.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":"999a29a2aa943ed5"}},{"code_sha256_prefix":"cdc3095e36a5efa7","entry":"lowercase_first","repo":"timoschick/pet","repo_kind":"found_in_text","path":"pet/utils.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/pet/utils.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":"cdc3095e36a5efa7"}},{"code_sha256_prefix":"cbf3175e3ec772a0","entry":"mask_tokens","repo":"matthewcym/sflm","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/utils.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":"cbf3175e3ec772a0"}},{"code_sha256_prefix":"20e328b05dd717e0","entry":"remove_final_punc","repo":"timoschick/pet","repo_kind":"found_in_text","path":"pet/utils.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/pet/utils.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":"20e328b05dd717e0"}},{"code_sha256_prefix":"72e4be6e6f4cdc7e","entry":"tokenize_multipart_input","repo":"matthewcym/sflm","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/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":"72e4be6e6f4cdc7e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}