{"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/distributed-representations-of-sentences-and","title":"Distributed Representations of Sentences and Documents","arxiv_id":"1405.4053","date":"2014-05-16","proceeding":null,"authors":["Quoc V. Le","Tomas Mikolov"],"abstract":"Many machine learning algorithms require the input to be represented as a\nfixed-length feature vector. When it comes to texts, one of the most common\nfixed-length features is bag-of-words. Despite their popularity, bag-of-words\nfeatures have two major weaknesses: they lose the ordering of the words and\nthey also ignore semantics of the words. For example, \"powerful,\" \"strong\" and\n\"Paris\" are equally distant. In this paper, we propose Paragraph Vector, an\nunsupervised algorithm that learns fixed-length feature representations from\nvariable-length pieces of texts, such as sentences, paragraphs, and documents.\nOur algorithm represents each document by a dense vector which is trained to\npredict words in the document. Its construction gives our algorithm the\npotential to overcome the weaknesses of bag-of-words models. Empirical results\nshow that Paragraph Vectors outperform bag-of-words models as well as other\ntechniques for text representations. Finally, we achieve new state-of-the-art\nresults on several text classification and sentiment analysis tasks.","url_abs":"http://arxiv.org/abs/1405.4053v2","url_pdf":"http://arxiv.org/pdf/1405.4053v2.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":"distributed-representations-of-sentences-and","repo_url":"https://github.com/Antonildo43/Classifica-o-de-textos-com-doc2Vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/DCYN/Ramdomized-Clinical-Trail-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/Nalydy/doc2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/TheCyberian/androidMalwareDetectionWithNLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/TheCyberian/windowsMalwareDetectionWithNLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distributed-representations-of-sentences-and","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":"distributed-representations-of-sentences-and","repo_url":"https://github.com/bombdiggity/paper-bag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/dhyeon/ingredient-vectors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/eske/multivec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/fabiocorreacordeiro/Elsevier_abstracts-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/g-k-l/dsi-arxiv-recommender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/hithisisdhara/doc2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/ibrahimsharaf/doc2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/inejc/paragraph-vectors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/jimmy6727/Informd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/julian-risch/ICADL2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/kinimod23/NMT_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/kitnhl/partisan-tweets-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/kr900910/supreme_court_opinion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/kramamur/sentiment-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/rvstraalen/doc2vec-workshop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/slme1109/Lyrics_Generator_Using_LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/slme1109/lyrics-generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/tsandefer/capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/tsandefer/dsi_capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/vanboefer/nn_doc2vec_exercise","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"distributed-representations-of-sentences-and","repo_url":"https://github.com/wiflore/IBM_Articles_Recomender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-qasent","task":"Question Answering","dataset":"QASent","model":"Paragraph vector (lexical overlap + dist output)","rank_in_archive_order":4,"of":7,"metrics":{"MAP":"0.6762","MRR":"0.7514"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-qasent","task":"Question Answering","dataset":"QASent","model":"Paragraph vector","rank_in_archive_order":7,"of":7,"metrics":{"MAP":"0.5213","MRR":"0.6023"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"Paragraph vector (lexical overlap + dist output)","rank_in_archive_order":24,"of":25,"metrics":{"MAP":"0.5976","MRR":" 0.6058"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"Paragraph vector","rank_in_archive_order":25,"of":25,"metrics":{"MAP":"0.5110","MRR":"0.5160"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-imdb","task":"Text Classification","dataset":"IMDb","model":"Paragraph Vectors Le & Mikolov (2014)","rank_in_archive_order":3,"of":13,"metrics":{},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1405.4053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1405.4053"}},"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/bombdiggity/paper-bag","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jimmy6727/Informd","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TheCyberian/windowsMalwareDetectionWithNLP","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/julian-risch/ICADL2018","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hithisisdhara/doc2vec","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/inejc/paragraph-vectors","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fabiocorreacordeiro/Elsevier_abstracts-Classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kr900910/supreme_court_opinion","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsandefer/capstone_2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DCYN/Ramdomized-Clinical-Trail-Classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vanboefer/nn_doc2vec_exercise","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsandefer/dsi_capstone_2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eske/multivec","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kitnhl/partisan-tweets-classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nalydy/doc2vec","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibrahimsharaf/doc2vec","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/g-k-l/dsi-arxiv-recommender","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TheCyberian/androidMalwareDetectionWithNLP","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/slme1109/Lyrics_Generator_Using_LSTM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dhyeon/ingredient-vectors","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kramamur/sentiment-analysis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/slme1109/lyrics-generator","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wiflore/IBM_Articles_Recomender","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Antonildo43/Classifica-o-de-textos-com-doc2Vec","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rvstraalen/doc2vec-workshop","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"5c8561d39b5f3185","entry":"extract_name_attribute_from_xml","repo":"TheCyberian/windowsMalwareDetectionWithNLP","repo_kind":"listed","path":"xml2strings.py","file_url":"https://github.com/TheCyberian/windowsMalwareDetectionWithNLP/blob/HEAD/xml2strings.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":"5c8561d39b5f3185"}},{"code_sha256_prefix":"ffa4cd04f2875291","entry":"list_dir","repo":"TheCyberian/androidMalwareDetectionWithNLP","repo_kind":"listed","path":"doc2vec_training_plus_binary_classification.py","file_url":"https://github.com/TheCyberian/androidMalwareDetectionWithNLP/blob/HEAD/doc2vec_training_plus_binary_classification.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":"ffa4cd04f2875291"}},{"code_sha256_prefix":"e53b2b396184b0c0","entry":"logistic_predictor_from_sklearn","repo":"TheCyberian/androidMalwareDetectionWithNLP","repo_kind":"listed","path":"doc2vec_training_plus_binary_classification.py","file_url":"https://github.com/TheCyberian/androidMalwareDetectionWithNLP/blob/HEAD/doc2vec_training_plus_binary_classification.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":"e53b2b396184b0c0"}},{"code_sha256_prefix":"4aa99ad90bcb852d","entry":"retrieve_vectors","repo":"TheCyberian/androidMalwareDetectionWithNLP","repo_kind":"listed","path":"utilities/vectorize_csv.py","file_url":"https://github.com/TheCyberian/androidMalwareDetectionWithNLP/blob/HEAD/utilities/vectorize_csv.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":"4aa99ad90bcb852d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}