{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/word-embeddings/papers/17","list_of":"/task/word-embeddings","task":"Word Embeddings","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":17,"pages_in_order":41,"rows_per_page":100,"rows":[1601,1700],"of":4002,"counts":{"archive_papers_tagged":4002,"with_a_code_link":1177,"where_syntology_ran_a_sample":155,"not_listed_spam_title":0,"listed":4002,"listed_where_code_ran":155,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":122,"every_run_a_failure_of_syntologys_instrument":33,"listed_with_a_run_with_no_instrument_failure":122,"listed_every_run_a_failure_of_syntologys_instrument":33,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/word-embeddings","prev":"/task/word-embeddings/papers/16","next":"/task/word-embeddings/papers/18","papers":[{"url":null,"slug":"retrofitting-of-pre-trained-emotion-words","title":"Retrofitting of Pre-trained Emotion Words with VAD-dimensions and the Plutchik Emotions","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sdutta-at-comma-icon-a-cnn-lstm-model-for","title":"Sdutta at ComMA@ICON: A CNN-LSTM Model for Hate Detection","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-word-embeddings-to-quantify-ethnic","title":"Using Word Embeddings to Quantify Ethnic Stereotypes in 12 years of Spanish News","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-transformers-on-word","title":"A Comparative Study of Transformers on Word Sense Disambiguation","date":"2021-11-30","arxiv_id":"2111.15417","repositories_listed":0,"syntology":null},{"url":null,"slug":"bilingual-topic-models-for-comparable-corpora","title":"Bilingual Topic Models for Comparable Corpora","date":"2021-11-30","arxiv_id":"2111.15278","repositories_listed":0,"syntology":null},{"url":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-romanian-word-embeddings-from-the","title":"More Romanian word embeddings from the RETEROM project","date":"2021-11-21","arxiv_id":"2111.10750","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-word-embeddings-in-hyperbolic","title":"Cross-lingual Word Embeddings in Hyperbolic Space","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crossword-estimating-unknown-embeddings-using","title":"Crossword: Estimating Unknown Embeddings using Cross Attention and Alignment Strategies","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-unassimilated-borrowings-in-spanish","title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-wavelet-transform-for-efficient-word","title":"Discrete Wavelet Transform for Efficient Word Embeddings and Sentence Encoding","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feelsgoodman-inferring-semantics-of-twitch-1","title":"FeelsGoodMan: Inferring Semantics of Twitch Neologisms","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"first-bilingual-word-embeddings-for-te-reo","title":"First Bilingual Word Embeddings for te reo Māori and English: Towards Code-switching Detection in a Low-resourced setting","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-embeddings-to-understand","title":"Interpretable embeddings to understand computing careers","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-neural-topic-modelling-better-than","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"isomorphic-cross-lingual-embeddings-for-low","title":"Isomorphic Cross-lingual Embeddings for Low-Resource Languages","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-evaluating-character","title":"Learning and Evaluating Character Representations in Novels","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-into-the-black-box-how-are-idioms","title":"Looking Into the Black Box - How Are Idioms Processed in BERT?","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"metaphor-detection-for-low-resource-languages","title":"Metaphor Detection for Low Resource Languages: From Zero-Shot to Few-Shot Learning in Middle High German","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-framework-with-refinement-based","title":"Multi-Stage Framework with Refinement based Point Set Registration for Unsupervised Bi-Lingual Word Alignment","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"non-linear-relational-information-probing-in","title":"Non-Linear Relational Information Probing in Word Embeddings","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-interpretability-and-significance-of","title":"On the interpretability and significance of bias metrics in texts: a PMI-based approach","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-and-fine-tuning-neural-topic","title":"Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sense-embeddings-are-also-biased-evaluating","title":"Sense Embeddings are also Biased -- Evaluating Social Biases in Static and Contextualised Sense Embeddings","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-selection-strategies-for-distilling","title":"Sentence Selection Strategies for Distilling Word Embeddings from BERT","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"softmax-bottleneck-makes-language-models","title":"Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sos-systematic-offensive-stereotyping-bias-in","title":"SOS: Systematic Offensive Stereotyping Bias in Word Embeddings","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-with-8","title":"Unsupervised Domain Adaptation with Contrastive Learning for Cross-domain Chinese NER","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vec2node-self-training-with-tensor","title":"Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-metrics-for-bias-in-word","title":"Evaluating Metrics for Bias in Word Embeddings","date":"2021-11-15","arxiv_id":"2111.07864","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-semantic-space-by-grounding","title":"Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning","date":"2021-11-13","arxiv_id":"2111.07180","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyphrase-extraction-using-neighborhood","title":"Keyphrase Extraction Using Neighborhood Knowledge Based on Word Embeddings","date":"2021-11-13","arxiv_id":"2111.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-pii-extraction-from-social-media","title":"Automated PII Extraction from Social Media for Raising Privacy Awareness: A Deep Transfer Learning Approach","date":"2021-11-11","arxiv_id":"2111.09415","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-aware-latent-models-for-representation","title":"Topic-aware latent models for representation learning on networks","date":"2021-11-10","arxiv_id":"2111.05576","repositories_listed":0,"syntology":null},{"url":null,"slug":"monitoring-geometrical-properties-of-word-1","title":"Monitoring geometrical properties of word embeddings for detecting the emergence of new topics","date":"2021-11-05","arxiv_id":"2111.03496","repositories_listed":0,"syntology":null},{"url":null,"slug":"poshan-cardinal-pos-pattern-guided-attention","title":"POSHAN: Cardinal POS Pattern Guided Attention for News Headline Incongruence","date":"2021-11-05","arxiv_id":"2111.03547","repositories_listed":0,"syntology":null},{"url":null,"slug":"my-house-my-rules-learning-tidying","title":"My House, My Rules: Learning Tidying Preferences with Graph Neural Networks","date":"2021-11-04","arxiv_id":"2111.03112","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-advantages-of-interactive-and-non","title":"Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval","date":"2021-11-03","arxiv_id":"2111.01992","repositories_listed":0,"syntology":null},{"url":null,"slug":"bahp-benchmark-of-assessing-word-embeddings","title":"BAHP: Benchmark of Assessing Word Embeddings in Historical Portuguese","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"common-sense-bias-in-semantic-role-labeling","title":"Common Sense Bias in Semantic Role Labeling","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-word-embeddings-with-brain-based","title":"Decoding Word Embeddings with Brain-Based Semantic Features","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-conversational-data-and-detection","title":"Developing Conversational Data and Detection of Conversational Humor in Telugu","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"do-not-neglect-related-languages-the-case-of","title":"Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-topics-with-simultaneous-word-co","title":"Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Texts","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-sentence-level-comprehension","title":"Increasing Sentence-Level Comprehension Through Text Classification of Epistemic Functions","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-stance-detection-topic-independent-and-1","title":"Is Stance Detection Topic-Independent and Cross-topic Generalizable? - A Reproduction Study","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sense-specific-static-embeddings-1","title":"Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"locality-preserving-sentence-encoding","title":"Locality Preserving Sentence Encoding","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monitoring-geometrical-properties-of-word","title":"Monitoring geometrical properties of word embeddings for detecting the emergence of new topics.","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-machine-translation-for-tamil-telugu","title":"Neural Machine Translation for Tamil–Telugu Pair","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-cross-lingual-transferability-of-2","title":"On the Cross-lingual Transferability of Contextualized Sense Embeddings","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tracing-variation-in-discourse-connectives-in","title":"Tracing variation in discourse connectives in translation and interpreting through neural semantic spaces","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncle-explicitly-leveraging-semantic","title":"UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wikily-supervised-neural-translation-tailored","title":"“Wikily” Supervised Neural Translation Tailored to Cross-Lingual Tasks","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-equations-inherently-interpretable","title":"Word Equations: Inherently Interpretable Sparse Word Embeddings through Sparse Coding","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-cross-lingual-transfer-is-a-hard","title":"Zero-Shot Cross-Lingual Transfer is a Hard Baseline to Beat in German Fine-Grained Entity Typing","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-a-texts-fairness-dimensions-using","title":"Measuring a Texts Fairness Dimensions Using Machine Learning Based on Social Psychological Factors","date":"2021-10-29","arxiv_id":"2111.00086","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-golden-rule-as-a-heuristic-to-measure-the","title":"The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning","date":"2021-10-29","arxiv_id":"2111.00107","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-embeddings-for-topic-modeling-an","title":"Word embeddings for topic modeling: an application to the estimation of the economic policy uncertainty index","date":"2021-10-29","arxiv_id":"2111.00057","repositories_listed":0,"syntology":null},{"url":null,"slug":"hate-and-offensive-speech-detection-in-hindi","title":"Hate and Offensive Speech Detection in Hindi and Marathi","date":"2021-10-23","arxiv_id":"2110.12200","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-sense-an-investigation-of-sensory","title":"Inter-Sense: An Investigation of Sensory Blending in Fiction","date":"2021-10-19","arxiv_id":"2110.09710","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-semi-supervised-transfer-learning","title":"Cooperative Semi-Supervised Transfer Learning of Machine Reading Comprehension","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-meta-word-embeddings-by-unsupervised","title":"Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-based-cross-lingual-transfer-of","title":"Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wechsel-effective-initialization-of-subword","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-off-the-shelf-machine-listening","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","date":"2021-10-14","arxiv_id":"2110.07410","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-substitution-based-word-sense","title":"Large Scale Substitution-based Word Sense Induction","date":"2021-10-14","arxiv_id":"2110.07681","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-lexical-and-semantic-analysis","title":"Regionalized models for Spanish language variations based on Twitter","date":"2021-10-12","arxiv_id":"2110.06128","repositories_listed":0,"syntology":null},{"url":null,"slug":"offensive-language-detection-with-bert-based","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","date":"2021-10-11","arxiv_id":"2110.05133","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-word-embeddings-for-italian-crime-news","title":"Using Word Embeddings for Italian Crime News Categorization","date":"2021-10-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-loop-refinement-of-word","title":"Human-in-the-Loop Refinement of Word Embeddings","date":"2021-10-06","arxiv_id":"2110.02884","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-neural-word-embeddings","title":"A Survey On Neural Word Embeddings","date":"2021-10-05","arxiv_id":"2110.01804","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sense-specific-static-embeddings","title":"Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy","date":"2021-10-05","arxiv_id":"2110.02204","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-to-reveal-if-an-area-of-interest","title":"A Case Study to Reveal if an Area of Interest has a Trend in Ongoing Tweets Using Word and Sentence Embeddings","date":"2021-10-02","arxiv_id":"2110.00866","repositories_listed":0,"syntology":null},{"url":null,"slug":"aggregating-user-centric-and-post-centric","title":"Aggregating User-Centric and Post-Centric Sentiments from Social Media for Topical Stance Prediction","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-centered-collocating-topic-analysis","title":"Keyword-centered Collocating Topic Analysis","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dicoe-finsim-3-financial-hypernym-detection","title":"DICoE@FinSim-3: Financial Hypernym Detection using Augmented Terms and Distance-based Features","date":"2021-09-30","arxiv_id":"2109.14906","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-of-twitter-embeddings-and-temporal","title":"Variance of Twitter Embeddings and Temporal Trends of COVID-19 cases","date":"2021-09-30","arxiv_id":"2110.00031","repositories_listed":0,"syntology":null},{"url":null,"slug":"antonymy-synonymy-discrimination-through-the","title":"Antonymy-Synonymy Discrimination through the Repelling Parasiamese Neural Network","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"debiasing-pretrained-text-encoders-by-paying","title":"Debiasing Pretrained Text Encoders by Paying Attention to Paying Attention","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/edgar-corpus-billions-of-tokens-make-the","slug":"edgar-corpus-billions-of-tokens-make-the","title":"EDGAR-CORPUS: Billions of Tokens Make The World Go Round","date":"2021-09-29","arxiv_id":"2109.14394","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-nearest-neighbor-search-in","title":"Graph-based Nearest Neighbor Search in Hyperbolic Spaces","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-learning-topic-specific-word-and","title":"JOINTLY LEARNING TOPIC SPECIFIC WORD AND DOCUMENT EMBEDDING","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstructing-word-embeddings-via-scattered","title":"Reconstructing Word Embeddings via Scattered $k$-Sub-Embedding","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-and-mitigating-gender-bias-in","title":"Identifying and Mitigating Gender Bias in Hyperbolic Word Embeddings","date":"2021-09-28","arxiv_id":"2109.13767","repositories_listed":0,"syntology":null},{"url":null,"slug":"marked-attribute-bias-in-natural-language","title":"Marked Attribute Bias in Natural Language Inference","date":"2021-09-28","arxiv_id":"2109.14039","repositories_listed":0,"syntology":null},{"url":null,"slug":"lacking-the-embedding-of-a-word-look-it-up","title":"Lacking the embedding of a word? Look it up into a traditional dictionary","date":"2021-09-24","arxiv_id":"2109.11763","repositories_listed":0,"syntology":null},{"url":null,"slug":"invbert-text-reconstruction-from","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","date":"2021-09-21","arxiv_id":"2109.10104","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-query-by-example-speech-search-using","title":"Fast query-by-example speech search using separable model","date":"2021-09-18","arxiv_id":"2109.08870","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-word-embedding-learning-for","title":"Contrastive Word Embedding Learning for Neural Machine Translation","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-roles-from-word-embeddings-in-a","title":"Gender Roles from Word Embeddings in a Century of Children’s Books","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-adaptive-pre-training-of-language-models","title":"Task-adaptive Pre-training of Language Models with Word Embedding Regularization","date":"2021-09-17","arxiv_id":"2109.08354","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-feature-engineering-and-feature","title":"Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification","date":"2021-09-15","arxiv_id":"2109.07604","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-biomedical-bert-models-for","title":"Evaluating Biomedical BERT Models for Vocabulary Alignment at Scale in the UMLS Metathesaurus","date":"2021-09-14","arxiv_id":"2109.13348","repositories_listed":0,"syntology":null},{"url":null,"slug":"argot-a-glossary-of-terms-extracted-from-the","title":"ArGoT: A Glossary of Terms extracted from the arXiv","date":"2021-09-07","arxiv_id":"2109.02801","repositories_listed":0,"syntology":null},{"url":null,"slug":"rare-words-degenerate-all-words","title":"Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings","date":"2021-09-07","arxiv_id":"2109.03127","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-detection-of-contextual","title":"Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case","date":"2021-09-04","arxiv_id":"2109.01935","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exploratory-study-on-utilising-the-web-of","title":"An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining","date":"2021-09-03","arxiv_id":"2109.01411","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-system-for-automatic","title":"A Deep Learning System for Automatic Extraction of Typological Linguistic Information from Descriptive Grammars","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractive-document-summarization-with-word","title":"Abstractive Document Summarization with Word Embedding Reconstruction","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"e4242ca857b2f4eb2e63af7193e7c3703ecadf56a789a9480294bdc18b747790","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}