{"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/senteval-an-evaluation-toolkit-for-universal","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","arxiv_id":"1803.05449","date":"2018-03-14","proceeding":"LREC 2018 5","authors":["Alexis Conneau","Douwe Kiela"],"abstract":"We introduce SentEval, a toolkit for evaluating the quality of universal\nsentence representations. SentEval encompasses a variety of tasks, including\nbinary and multi-class classification, natural language inference and sentence\nsimilarity. The set of tasks was selected based on what appears to be the\ncommunity consensus regarding the appropriate evaluations for universal\nsentence representations. The toolkit comes with scripts to download and\npreprocess datasets, and an easy interface to evaluate sentence encoders. The\naim is to provide a fairer, less cumbersome and more centralized way for\nevaluating sentence representations.","url_abs":"http://arxiv.org/abs/1803.05449v1","url_pdf":"http://arxiv.org/pdf/1803.05449v1.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":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/facebookresearch/SentEval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/AmanDaVinci/Universal-Sentence-Representations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/HUSTLyn/SentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/applicaai/senteval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/facebookresearch/InferSent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/ganeshjawahar/interpret_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/gaotianyu1350/SentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/goel96vibhor/AdvSentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/nyu-mll/SentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/princeton-nlp/mabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"senteval-an-evaluation-toolkit-for-universal","repo_url":"https://github.com/sidak/SentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-similarity","task_name":"Sentence Similarity"}],"methods":[],"datasets_introduced":[{"slug":"senteval","name":"SentEval","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.05449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.05449"}},"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/facebookresearch/InferSent","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HUSTLyn/SentEval","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/princeton-nlp/mabel","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/goel96vibhor/AdvSentEval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-mll/SentEval","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ganeshjawahar/interpret_bert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AmanDaVinci/Universal-Sentence-Representations","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaotianyu1350/SentEval","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sidak/SentEval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/applicaai/senteval","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/SentEval","reach":null}],"summary":{"ran_draft_wrong":3,"ran_honours":2,"ran_violates":1,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"repositories":2}},"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":6,"samples":[{"code_sha256_prefix":"b0e91ad44f7c82ec","entry":"adversarialFunc","repo":"goel96vibhor/AdvSentEval","repo_kind":"listed","path":"examples/infersent.py","file_url":"https://github.com/goel96vibhor/AdvSentEval/blob/HEAD/examples/infersent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b0e91ad44f7c82ec"}},{"code_sha256_prefix":"e1c6e7d12d71cb6b","entry":"batcher","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e1c6e7d12d71cb6b"}},{"code_sha256_prefix":"ff910817bb9f0411","entry":"batcher","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ff910817bb9f0411"}},{"code_sha256_prefix":"af7388308de7ccb4","entry":"create_dictionary","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"af7388308de7ccb4"}},{"code_sha256_prefix":"d3816cc60711a3b2","entry":"dim","repo":"goel96vibhor/AdvSentEval","repo_kind":"listed","path":"examples/infersent.py","file_url":"https://github.com/goel96vibhor/AdvSentEval/blob/HEAD/examples/infersent.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d3816cc60711a3b2"}},{"code_sha256_prefix":"19d5c2686259a0af","entry":"get_wordvec","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"19d5c2686259a0af"}},{"code_sha256_prefix":"2d5b88d69edd2775","entry":"accuracy","repo":"AmanDaVinci/Universal-Sentence-Representations","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/AmanDaVinci/Universal-Sentence-Representations/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d5b88d69edd2775"}},{"code_sha256_prefix":"767c2dc546a32e8f","entry":"report_senteval","repo":"AmanDaVinci/Universal-Sentence-Representations","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/AmanDaVinci/Universal-Sentence-Representations/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"767c2dc546a32e8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}