{"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/skip-thought-vectors","title":"Skip-Thought Vectors","arxiv_id":"1506.06726","date":"2015-06-22","proceeding":"NeurIPS 2015 12","authors":["Ryan Kiros","Yukun Zhu","Ruslan Salakhutdinov","Richard S. Zemel","Antonio Torralba","Raquel Urtasun","Sanja Fidler"],"abstract":"We describe an approach for unsupervised learning of a generic, distributed\nsentence encoder. Using the continuity of text from books, we train an\nencoder-decoder model that tries to reconstruct the surrounding sentences of an\nencoded passage. Sentences that share semantic and syntactic properties are\nthus mapped to similar vector representations. We next introduce a simple\nvocabulary expansion method to encode words that were not seen as part of\ntraining, allowing us to expand our vocabulary to a million words. After\ntraining our model, we extract and evaluate our vectors with linear models on 8\ntasks: semantic relatedness, paraphrase detection, image-sentence ranking,\nquestion-type classification and 4 benchmark sentiment and subjectivity\ndatasets. The end result is an off-the-shelf encoder that can produce highly\ngeneric sentence representations that are robust and perform well in practice.\nWe will make our encoder publicly available.","url_abs":"http://arxiv.org/abs/1506.06726v1","url_pdf":"http://arxiv.org/pdf/1506.06726v1.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":"skip-thought-vectors","repo_url":"https://github.com/SathesanThavabalasingam/skipthoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/YinpeiDai/NAUM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/arukavina/baking-lyrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/bunny98/Text-to-Image-Using-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/chalothon/Skip-Thought","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/dashayushman/TAC-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/dwright37/phylogenetic-autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","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":"skip-thought-vectors","repo_url":"https://github.com/facebookresearch/SentEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/kushalpatil1997/text_to_image_synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/luweizhang/joint_embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/ryankiros/skip-thoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/soskek/bookcorpus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/soskek/homemade_bookcorpus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/thomasyue/tf2-skip-thoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"skip-thought-vectors","repo_url":"https://github.com/whitneysattler/Skip-Thoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-similarity-on-sick","task":"Semantic Similarity","dataset":"SICK","model":"combine-skip (Kiros et al., 2015)","rank_in_archive_order":2,"of":5,"metrics":{"MSE":"0.2687","Pearson Correlation":"0.8584","Spearman Correlation":"0.7916"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.06726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.06726"}},"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/kushalpatil1997/text_to_image_synthesis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soskek/bookcorpus","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dashayushman/TAC-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SathesanThavabalasingam/skipthoughts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chalothon/Skip-Thought","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soskek/homemade_bookcorpus","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dwright37/phylogenetic-autoencoder","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomasyue/tf2-skip-thoughts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whitneysattler/Skip-Thoughts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/SentEval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luweizhang/joint_embeddings","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arukavina/baking-lyrics","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryankiros/skip-thoughts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bunny98/Text-to-Image-Using-GAN","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YinpeiDai/NAUM","reach":{"status":"ok","spdx":"MIT"}}],"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":"8649dc66bd2fdb2a","entry":"F1_score","repo":"YinpeiDai/NAUM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/YinpeiDai/NAUM/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":"8649dc66bd2fdb2a"}},{"code_sha256_prefix":"116aa69fc98e98db","entry":"normalize","repo":"YinpeiDai/NAUM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/YinpeiDai/NAUM/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":"116aa69fc98e98db"}},{"code_sha256_prefix":"d2e3e1bbb7618d21","entry":"sub_UNK","repo":"YinpeiDai/NAUM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/YinpeiDai/NAUM/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":"d2e3e1bbb7618d21"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}