{"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/generating-datasets-with-pretrained-language","title":"Generating Datasets with Pretrained Language Models","arxiv_id":"2104.07540","date":"2021-04-15","proceeding":"EMNLP 2021 11","authors":["Timo Schick","Hinrich Schütze"],"abstract":"To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically outperforms the former, it requires great human effort to generate suitable datasets of sufficient size. In this paper, we show how PLMs can be leveraged to obtain high-quality sentence embeddings without the need for labeled data, finetuning or modifications to the pretraining objective: We utilize the generative abilities of large and high-performing PLMs to generate entire datasets of labeled text pairs from scratch, which we then use for finetuning much smaller and more efficient models. Our fully unsupervised approach outperforms strong baselines on several semantic textual similarity datasets.","url_abs":"https://arxiv.org/abs/2104.07540v3","url_pdf":"https://arxiv.org/pdf/2104.07540v3.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":"generating-datasets-with-pretrained-language","repo_url":"https://github.com/timoschick/dino","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"generating-datasets-with-pretrained-language","repo_url":"https://github.com/yipingnus/scratchplot-story-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-textual-similarity-on-sick","task":"Semantic Textual Similarity","dataset":"SICK","model":"Dino (STS/̄🦕)","rank_in_archive_order":9,"of":22,"metrics":{"Spearman Correlation":"0.7426"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sick","task":"Semantic Textual Similarity","dataset":"SICK","model":"Dino (STSb/̄🦕)","rank_in_archive_order":19,"of":22,"metrics":{"Spearman Correlation":"0.6809"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"Dino (STSb/̄🦕)","rank_in_archive_order":55,"of":66,"metrics":{"Spearman Correlation":"0.7782"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"Dino (STS/̄🦕)","rank_in_archive_order":58,"of":66,"metrics":{"Spearman Correlation":"0.7651"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts12","task":"Semantic Textual Similarity","dataset":"STS12","model":"Dino (STSb/̄🦕)","rank_in_archive_order":14,"of":20,"metrics":{"Spearman Correlation":"0.7027"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts13","task":"Semantic Textual Similarity","dataset":"STS13","model":"Dino (STSb/̄🦕)","rank_in_archive_order":18,"of":22,"metrics":{"Spearman Correlation":"0.8126"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"Dino (STSb/̄🦕)","rank_in_archive_order":19,"of":21,"metrics":{"Spearman Correlation":"0.7125"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts15","task":"Semantic Textual Similarity","dataset":"STS15","model":"Dino (STSb/)","rank_in_archive_order":17,"of":20,"metrics":{"Spearman Correlation":"0.8049"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"Dino (STSb/̄🦕)","rank_in_archive_order":17,"of":20,"metrics":{"Spearman Correlation":"0.7718"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.07540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07540"}},"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/yipingnus/scratchplot-story-generation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/timoschick/dino","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"003c442d9c01a497","entry":"read_inputs","repo":"yipingnus/scratchplot-story-generation","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/yipingnus/scratchplot-story-generation/blob/HEAD/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":"003c442d9c01a497"}},{"code_sha256_prefix":"ba94c4cb5a503946","entry":"read_jsonl_inputs","repo":"yipingnus/scratchplot-story-generation","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/yipingnus/scratchplot-story-generation/blob/HEAD/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":"ba94c4cb5a503946"}},{"code_sha256_prefix":"a8784da93958c3c8","entry":"read_plaintext_inputs","repo":"yipingnus/scratchplot-story-generation","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/yipingnus/scratchplot-story-generation/blob/HEAD/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":"a8784da93958c3c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}