{"url":"/task/word-embeddings","name":"Word Embeddings","slug":"word-embeddings","description_markdown":"Word embedding is the collective name for a set of language modeling and feature learning techniques in natural language processing (NLP) where words or phrases from the vocabulary are mapped to vectors of real numbers.\r\n\r\nTechniques for learning word embeddings can include  Word2Vec, GloVe, and other neural network-based approaches that train on an NLP task such as language modeling or document classification.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Dynamic Word Embedding for Evolving Semantic Discovery](https://arxiv.org/pdf/1703.00607v2.pdf) )</span>","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4002,"papers_with_code":1177,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":52,"subtasks":4,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/conceptnet","name":"ConceptNet","full_name":"","num_papers_in_archive":852},{"url":"/dataset/framenet","name":"FrameNet","full_name":"","num_papers_in_archive":444},{"url":"/dataset/bookcorpus","name":"BookCorpus","full_name":"","num_papers_in_archive":344},{"url":"/dataset/wic","name":"WiC","full_name":"Words in Context","num_papers_in_archive":206},{"url":"/dataset/bioasq","name":"BioASQ","full_name":"Biomedical Semantic Indexing and Question Answering","num_papers_in_archive":192},{"url":"/dataset/billion-word-benchmark","name":"Billion Word Benchmark","full_name":"","num_papers_in_archive":141},{"url":"/dataset/winobias","name":"WinoBias","full_name":"WinoBias","num_papers_in_archive":134},{"url":"/dataset/padchest","name":"PadChest","full_name":"","num_papers_in_archive":116},{"url":"/dataset/wikimatrix","name":"WikiMatrix","full_name":"","num_papers_in_archive":91},{"url":"/dataset/wikiann-1","name":"WikiANN","full_name":"PAN-X","num_papers_in_archive":72},{"url":"/dataset/celex","name":"CELEX","full_name":"CELEX","num_papers_in_archive":59},{"url":"/dataset/isear","name":"ISEAR","full_name":"International Survey on Emotion Antecedents and Reactions","num_papers_in_archive":55},{"url":"/dataset/panlex","name":"Panlex","full_name":"","num_papers_in_archive":36},{"url":"/dataset/evalution","name":"EVALution","full_name":"EVALution","num_papers_in_archive":28},{"url":"/dataset/senseval-2-1","name":"Senseval-2","full_name":"Senseval-2","num_papers_in_archive":19},{"url":"/dataset/united-nations-parallel-corpus","name":"United Nations Parallel Corpus","full_name":"","num_papers_in_archive":18},{"url":"/dataset/card-660","name":"CARD-660","full_name":"","num_papers_in_archive":10},{"url":"/dataset/polyglot-ner","name":"Polyglot-NER","full_name":"","num_papers_in_archive":10},{"url":"/dataset/indosum","name":"IndoSum","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/era","name":"ERA","full_name":"Event Recognition in Aerial videos","num_papers_in_archive":8},{"url":"/dataset/send","name":"SEND","full_name":"Stanford Emotional Narratives Dataset","num_papers_in_archive":8},{"url":"/dataset/book-cover-dataset","name":"Book Cover Dataset","full_name":"","num_papers_in_archive":7},{"url":"/dataset/bengali-hate-speech","name":"Bengali Hate Speech","full_name":"","num_papers_in_archive":6},{"url":"/dataset/sts-2014","name":"SemEval-2014 Task-10","full_name":"","num_papers_in_archive":6},{"url":"/dataset/wikineural","name":"WikiNEuRal","full_name":"","num_papers_in_archive":6},{"url":"/dataset/wnlampro","name":"WNLaMPro","full_name":"WordNet Language Model Probing","num_papers_in_archive":6},{"url":"/dataset/sp-10k","name":"SP-10K","full_name":"","num_papers_in_archive":5},{"url":"/dataset/anlamver","name":"AnlamVer","full_name":"","num_papers_in_archive":4},{"url":"/dataset/some-like-it-hoax","name":"Some Like it Hoax","full_name":"","num_papers_in_archive":4},{"url":"/dataset/wikisem500","name":"WikiSem500","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/italian-crime-news","name":"DICE: a Dataset of Italian Crime Event news","full_name":"from Gazzetta di Modena [2011-2021]","num_papers_in_archive":3},{"url":"/dataset/hcu400","name":"HCU400","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/indicnlp-corpus","name":"IndicNLP Corpus","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/semcat","name":"SEMCAT","full_name":"","num_papers_in_archive":3},{"url":"/dataset/chinese-gigaword","name":"Chinese Gigaword","full_name":"Chinese Gigaword","num_papers_in_archive":2},{"url":"/dataset/climate-claims","name":"Climate Claims","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/japanese-word-similarity","name":"Japanese Word Similarity","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/muse","name":"MUSE","full_name":"MUSE","num_papers_in_archive":2},{"url":"/dataset/pioner","name":"pioNER","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/sart","name":"SART","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/skill2vec","name":"Skill2vec","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bangla-word-analogy-1","name":"Bangla Word Analogy","full_name":"Bangla Word Analogy","num_papers_in_archive":1},{"url":"/dataset/gloreplus","name":"GloREPlus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ilur-news-texts","name":"iLur News Texts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/interpretable-sts","name":"Interpretable STS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kawat","name":"KaWAT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/larqs","name":"LARQS","full_name":"An Evaluation Dataset for Chinese Codex Word Embedding Model","num_papers_in_archive":1},{"url":"/dataset/mcqueen","name":"McQueen","full_name":"","num_papers_in_archive":1},{"url":"/dataset/riskdata","name":"RiskData","full_name":"","num_papers_in_archive":1},{"url":"/dataset/twitter-death-hoaxes","name":"Twitter Death Hoaxes","full_name":"","num_papers_in_archive":1},{"url":"/dataset/urban-dict-spelling-variant","name":"Urban Dict spelling variant","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bangla-word-analogy","name":"Word Analogy Bangla","full_name":"Word Analogy Bangla","num_papers_in_archive":0}],"subtasks":[{"url":"/task/contextualised-word-representations","name":"Contextualised Word Representations"},{"url":"/task/embeddings-evaluation","name":"Embeddings Evaluation"},{"url":"/task/learning-word-embeddings","name":"Learning Word Embeddings"},{"url":"/task/multilingual-word-embeddings","name":"Multilingual Word Embeddings"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":1177,"tagged_in_all":4002,"items":[{"url":"/paper/enriching-word-vectors-with-subword","title":"Enriching Word Vectors with Subword Information","date":"2016-07-15","arxiv_id":"1607.04606","repositories_listed":54,"syntology":{"n":31,"n_ran":4,"n_unverified":27,"n_pointer_only":4}},{"url":"/paper/fasttextzip-compressing-text-classification","title":"FastText.zip: Compressing text classification models","date":"2016-12-12","arxiv_id":"1612.03651","repositories_listed":44,"syntology":{"n":18,"n_ran":3,"n_unverified":15,"n_pointer_only":12}},{"url":"/paper/universal-sentence-encoder","title":"Universal Sentence Encoder","date":"2018-03-29","arxiv_id":"1803.11175","repositories_listed":24,"syntology":{"n":22,"n_ran":1,"n_unverified":21,"n_pointer_only":1}},{"url":"/paper/supervised-learning-of-universal-sentence","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","date":"2017-05-05","arxiv_id":"1705.02364","repositories_listed":23,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/word-translation-without-parallel-data","title":"Word Translation Without Parallel Data","date":"2017-10-11","arxiv_id":"1710.04087","repositories_listed":20,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/evaluation-of-sentence-embeddings-in","title":"Evaluation of sentence embeddings in downstream and linguistic probing tasks","date":"2018-06-16","arxiv_id":"1806.06259","repositories_listed":14,"syntology":null},{"url":"/paper/named-entity-recognition-with-bidirectional","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","date":"2015-11-26","arxiv_id":"1511.08308","repositories_listed":14,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":4}},{"url":"/paper/topic-modeling-in-embedding-spaces","title":"Topic Modeling in Embedding Spaces","date":"2019-07-08","arxiv_id":"1907.04907","repositories_listed":12,"syntology":{"n":13,"n_ran":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/train-short-test-long-attention-with-linear","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","date":"2021-08-27","arxiv_id":"2108.12409","repositories_listed":10,"syntology":{"n":16,"n_ran":13,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/breaking-the-softmax-bottleneck-a-high-rank","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","date":"2017-11-10","arxiv_id":"1711.03953","repositories_listed":9,"syntology":{"n":23,"n_ran":1,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/man-is-to-computer-programmer-as-woman-is-to","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","date":"2016-07-21","arxiv_id":"1607.06520","repositories_listed":8,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/emoji2vec-learning-emoji-representations-from","title":"emoji2vec: Learning Emoji Representations from their Description","date":"2016-09-27","arxiv_id":"1609.08359","repositories_listed":7,"syntology":null},{"url":"/paper/building-end-to-end-dialogue-systems-using","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","date":"2015-07-17","arxiv_id":"1507.04808","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/optimal-hyperparameters-for-deep-lstm","title":"Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks","date":"2017-07-21","arxiv_id":"1707.06799","repositories_listed":6,"syntology":null},{"url":"/paper/bb_twtr-at-semeval-2017-task-4-twitter","title":"BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs","date":"2017-04-20","arxiv_id":"1704.06125","repositories_listed":6,"syntology":null},{"url":"/paper/conceptnet-55-an-open-multilingual-graph-of","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","date":"2016-12-12","arxiv_id":"1612.03975","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/diachronic-word-embeddings-reveal-statistical","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","date":"2016-05-30","arxiv_id":"1605.09096","repositories_listed":6,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/transformers-without-tears-improving-the","title":"Transformers without Tears: Improving the Normalization of Self-Attention","date":"2019-10-14","arxiv_id":"1910.05895","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/supertml-two-dimensional-word-embedding-and","title":"SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data","date":"2019-02-26","arxiv_id":"1903.06246","repositories_listed":5,"syntology":null},{"url":"/paper/unsupervised-learning-of-sentence-embeddings","title":"Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features","date":"2017-03-07","arxiv_id":"1703.02507","repositories_listed":5,"syntology":null},{"url":"/paper/mixing-dirichlet-topic-models-and-word","title":"Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec","date":"2016-05-06","arxiv_id":"1605.02019","repositories_listed":5,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/document-embedding-with-paragraph-vectors","title":"Document Embedding with Paragraph Vectors","date":"2015-07-29","arxiv_id":"1507.07998","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/word2vec-explained-deriving-mikolov-et-als","title":"word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method","date":"2014-02-15","arxiv_id":"1402.3722","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/multi-relational-embedding-for-knowledge","title":"Multi-Relational Embedding for Knowledge Graph Representation and Analysis","date":"2020-09-28","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/cycle-text-to-image-gan-with-bert","title":"Cycle Text-To-Image GAN with BERT","date":"2020-03-26","arxiv_id":"2003.12137","repositories_listed":4,"syntology":null},{"url":"/paper/a-general-framework-for-implicit-and-explicit","title":"A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces","date":"2019-09-13","arxiv_id":"1909.06092","repositories_listed":4,"syntology":{"n":19,"n_ran":1,"n_unverified":18,"n_pointer_only":1}},{"url":"/paper/using-text-embeddings-for-causal-inference","title":"Adapting Text Embeddings for Causal Inference","date":"2019-05-29","arxiv_id":"1905.12741","repositories_listed":4,"syntology":null},{"url":"/paper/few-shot-learning-for-named-entity","title":"Few-shot Learning for Named Entity Recognition in Medical Text","date":"2018-11-13","arxiv_id":"1811.05468","repositories_listed":4,"syntology":null},{"url":"/paper/biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","arxiv_id":"1810.09302","repositories_listed":4,"syntology":null},{"url":"/paper/unsupervised-abstractive-meeting","title":"Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization","date":"2018-05-14","arxiv_id":"1805.05271","repositories_listed":4,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}