{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/exploiting-cloze-questions-for-few-shot-text","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","arxiv_id":"2001.07676","date":"2020-01-21","proceeding":null,"authors":["Timo Schick","Hinrich Schütze"],"abstract":"Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with \"task descriptions\" in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart, we show in this work that the two ideas can be combined: We introduce Pattern-Exploiting Training (PET), a semi-supervised training procedure that reformulates input examples as cloze-style phrases to help language models understand a given task. These phrases are then used to assign soft labels to a large set of unlabeled examples. Finally, standard supervised training is performed on the resulting training set. For several tasks and languages, PET outperforms supervised training and strong semi-supervised approaches in low-resource settings by a large margin.","url_abs":"https://arxiv.org/abs/2001.07676v3","url_pdf":"https://arxiv.org/pdf/2001.07676v3.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":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/timoschick/pet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/Wattsy2020/closure_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/idc-dsi/Arapet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/sunyilgdx/prompts4keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/pet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"exploiting-cloze-questions-for-few-shot-text","repo_url":"https://github.com/alibaba/EasyNLP/tree/master/examples/fewshot_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"few-shot-text-classification","task_name":"Few-Shot Text Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"pattern-exploiting-training","method_name":"Pattern-Exploiting Training"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pattern-exploiting-training","name":"Pattern-Exploiting Training","full_name":"Pattern-Exploiting Training"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.07676","atlas_url":"https://app.syntology.ai/?focus=2001.07676","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2001.07676"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2001.07676\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2001.07676"},"call":"get_concepts_for_paper(arxiv_id=\"2001.07676\")"}],"by_repo":[{"repo":"timoschick/pet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.01256"],"harvested_for_calls":[{"arxiv_id":"2110.01256","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.01256"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.01256\")"}]},{"repo":"Wattsy2020/closure_learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"idc-dsi/Arapet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sunyilgdx/prompts4keras","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.14690"],"harvested_for_calls":[{"arxiv_id":"2104.14690","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.14690"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.14690\")"}]},{"repo":"PaddlePaddle/PaddleNLP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.03416"],"harvested_for_calls":[{"arxiv_id":"2301.03416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.03416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.03416\")"}]},{"repo":"alibaba/EasyNLP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.06761"],"harvested_for_calls":[{"arxiv_id":"2311.06761","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.06761"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.06761\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"34b29eeb55a25776d4091cd811be93e101bce6fd6d52e313a34454fde2acb00b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}