{"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/protaugment-unsupervised-diverse-short-texts","title":"ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning","arxiv_id":"2105.12995","date":"2021-05-27","proceeding":null,"authors":["Thomas Dopierre","Christophe Gravier","Wilfried Logerais"],"abstract":"Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of Prototypical Networks, that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data, and then fueled to the Prototypical Network training objective as a consistency loss. ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain.","url_abs":"https://arxiv.org/abs/2105.12995v1","url_pdf":"https://arxiv.org/pdf/2105.12995v1.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":"protaugment-unsupervised-diverse-short-texts","repo_url":"https://github.com/tdopierre/ProtAugment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12995"}},"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/tdopierre/ProtAugment","reach":null}],"summary":{"ran":1,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"1c8ed81c2afae8c0","entry":"FewShotDataset","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"none","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1c8ed81c2afae8c0"}},{"code_sha256_prefix":"3ae294e827bbb579","entry":"cosine_similarity","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ae294e827bbb579"}},{"code_sha256_prefix":"0487849f056bb900","entry":"get_jsonl_data","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0487849f056bb900"}},{"code_sha256_prefix":"1f7856529205269a","entry":"get_txt_data","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f7856529205269a"}},{"code_sha256_prefix":"4866268f11cbb765","entry":"BERTEncoder","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","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":"4866268f11cbb765"}},{"code_sha256_prefix":"1c64c175ce7fd8f8","entry":"ProtAugmentNet","repo":"tdopierre/ProtAugment","repo_kind":"official","path":"models/proto/protaugment.py","file_url":"https://github.com/tdopierre/ProtAugment/blob/HEAD/models/proto/protaugment.py","link_basis":"first_harvest_node","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":"1c64c175ce7fd8f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}