{"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":"/method/linear-warmup-with-linear-decay/papers/38","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear Decay","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":38,"pages_in_order":71,"rows_per_page":100,"rows":[3701,3800],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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":"/method/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/37","next":"/method/linear-warmup-with-linear-decay/papers/39","papers":[{"paper":"/paper/towards-explainable-evaluation-metrics-for","slug":"towards-explainable-evaluation-metrics-for","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","date":"2022-03-21","arxiv_id":"2203.11131","n_code_links":1,"syntology":null},{"paper":"/paper/build-a-robust-qa-system-with-transformer","slug":"build-a-robust-qa-system-with-transformer","title":"Build a Robust QA System with Transformer-based Mixture of Experts","date":"2022-03-20","arxiv_id":"2204.09598","n_code_links":1,"syntology":null},{"paper":"/paper/cluster-tune-boost-cold-start-performance-in","slug":"cluster-tune-boost-cold-start-performance-in","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","date":"2022-03-20","arxiv_id":"2203.10581","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["ibm/intermediate-training-using-clustering"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","slug":"g2pw-a-conditional-weighted-softmax-bert-for","title":"g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin","date":"2022-03-20","arxiv_id":"2203.10430","n_code_links":1,"syntology":null},{"paper":"/paper/how-does-the-pre-training-objective-affect-1","slug":"how-does-the-pre-training-objective-affect-1","title":"How does the pre-training objective affect what large language models learn about linguistic properties?","date":"2022-03-20","arxiv_id":"2203.10415","n_code_links":1,"syntology":null},{"paper":"/paper/perturbations-in-the-wild-leveraging-human-1","slug":"perturbations-in-the-wild-leveraging-human-1","title":"Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense","date":"2022-03-19","arxiv_id":"2203.10346","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lethaiq/perturbations-in-the-wild"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entropy-based-attention-regularization-frees","slug":"entropy-based-attention-regularization-frees","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","date":"2022-03-17","arxiv_id":"2203.09192","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["g8a9/ear"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fine-and-coarse-granularity-hybrid-self","slug":"fine-and-coarse-granularity-hybrid-self","title":"Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT","date":"2022-03-17","arxiv_id":"2203.09055","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-detection-of-personal-employment","slug":"multilingual-detection-of-personal-employment","title":"Multilingual Detection of Personal Employment Status on Twitter","date":"2022-03-17","arxiv_id":"2203.09178","n_code_links":1,"syntology":null},{"paper":"/paper/adapler-speeding-up-inference-by-adaptive-1","slug":"adapler-speeding-up-inference-by-adaptive-1","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","date":"2022-03-16","arxiv_id":"2203.08991","n_code_links":1,"syntology":null},{"paper":"/paper/kinyabert-a-morphology-aware-kinyarwanda-1","slug":"kinyabert-a-morphology-aware-kinyarwanda-1","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","date":"2022-03-16","arxiv_id":"2203.08459","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":2,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["anzeyimana/kinyabert-acl2022"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/label-semantics-for-few-shot-named-entity","slug":"label-semantics-for-few-shot-named-entity","title":"Label Semantics for Few Shot Named Entity Recognition","date":"2022-03-16","arxiv_id":"2203.08985","n_code_links":1,"syntology":null},{"paper":"/paper/data-contamination-from-memorization-to-1","slug":"data-contamination-from-memorization-to-1","title":"Data Contamination: From Memorization to Exploitation","date":"2022-03-15","arxiv_id":"2203.08242","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["schwartz-lab-nlp/data_contamination"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/do-berts-learn-to-use-browser-user-interface-1","slug":"do-berts-learn-to-use-browser-user-interface-1","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","date":"2022-03-15","arxiv_id":"2203.07828","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["Alab-NII/bertbui_pub"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/imputing-out-of-vocabulary-embeddings-with","slug":"imputing-out-of-vocabulary-embeddings-with","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost","date":"2022-03-15","arxiv_id":"2203.07860","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tigerchen52/love"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"can-pre-trained-transformers-be-used-in","title":"Can pre-trained Transformers be used in detecting complex sensitive sentences? -- A Monsanto case study","date":"2022-03-14","arxiv_id":"2203.06793","n_code_links":0,"syntology":null},{"paper":"/paper/the-optimal-bert-surgeon-scalable-and","slug":"the-optimal-bert-surgeon-scalable-and","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","date":"2022-03-14","arxiv_id":"2203.07259","n_code_links":1,"syntology":null},{"paper":null,"slug":"wcl-bbcd-a-contrastive-learning-and-knowledge","title":"WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition","date":"2022-03-14","arxiv_id":"2203.06925","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-impact-of-covid-19-on","title":"Investigating the Impact of COVID-19 on Education by Social Network Mining","date":"2022-03-13","arxiv_id":"2203.06584","n_code_links":0,"syntology":null},{"paper":"/paper/scinli-a-corpus-for-natural-language","slug":"scinli-a-corpus-for-natural-language","title":"SciNLI: A Corpus for Natural Language Inference on Scientific Text","date":"2022-03-13","arxiv_id":"2203.06728","n_code_links":1,"syntology":null},{"paper":"/paper/bibert-accurate-fully-binarized-bert-1","slug":"bibert-accurate-fully-binarized-bert-1","title":"BiBERT: Accurate Fully Binarized BERT","date":"2022-03-12","arxiv_id":"2203.06390","n_code_links":1,"syntology":null},{"paper":"/paper/elle-efficient-lifelong-pre-training-for-1","slug":"elle-efficient-lifelong-pre-training-for-1","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2022-03-12","arxiv_id":"2203.06311","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thunlp/elle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/finer-financial-numeric-entity-recognition","slug":"finer-financial-numeric-entity-recognition","title":"FiNER: Financial Numeric Entity Recognition for XBRL Tagging","date":"2022-03-12","arxiv_id":"2203.06482","n_code_links":2,"syntology":null},{"paper":"/paper/markbert-marking-word-boundaries-improves-1","slug":"markbert-marking-word-boundaries-improves-1","title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT","date":"2022-03-12","arxiv_id":"2203.06378","n_code_links":1,"syntology":null},{"paper":"/paper/a-sentence-is-worth-128-pseudo-tokens-a-1","slug":"a-sentence-is-worth-128-pseudo-tokens-a-1","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","date":"2022-03-11","arxiv_id":"2203.05877","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["namco0816/pt-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertopic-neural-topic-modeling-with-a-class","slug":"bertopic-neural-topic-modeling-with-a-class","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","date":"2022-03-11","arxiv_id":"2203.05794","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["MaartenGr/BERTopic","maartengr/bertopic_evaluation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"hierarchical-bert-for-medical-document","title":"Hierarchical BERT for Medical Document Understanding","date":"2022-03-11","arxiv_id":"2204.09600","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-word-embeddings-to-analyze-protests","title":"Using Word Embeddings to Analyze Protests News","date":"2022-03-11","arxiv_id":"2203.05875","n_code_links":0,"syntology":null},{"paper":"/paper/verbert-automating-brazilian-case-law","slug":"verbert-automating-brazilian-case-law","title":"verBERT: Automating Brazilian Case Law Document Multi-label Categorization Using BERT","date":"2022-03-11","arxiv_id":"2203.06224","n_code_links":1,"syntology":null},{"paper":"/paper/when-classifying-grammatical-role-bert-doesn-1","slug":"when-classifying-grammatical-role-bert-doesn-1","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2022-03-11","arxiv_id":"2203.06204","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-approach-to-calculating-bertscore-for","title":"A new approach to calculating BERTScore for automatic assessment of translation quality","date":"2022-03-10","arxiv_id":"2203.05598","n_code_links":0,"syntology":null},{"paper":"/paper/contextualized-sensorimotor-norms-multi-1","slug":"contextualized-sensorimotor-norms-multi-1","title":"Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context","date":"2022-03-10","arxiv_id":"2203.05648","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-norm-recognition-and-its-application","title":"Semantic Norm Recognition and its application to Portuguese Law","date":"2022-03-10","arxiv_id":"2203.05425","n_code_links":0,"syntology":null},{"paper":"/paper/speciesist-language-and-nonhuman-animal-bias-1","slug":"speciesist-language-and-nonhuman-animal-bias-1","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","date":"2022-03-10","arxiv_id":"2203.05140","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-generalized-models-for-task-oriented","title":"Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations","date":"2022-03-08","arxiv_id":"2203.04045","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-token-replaced-detection-model-as","slug":"pre-trained-token-replaced-detection-model-as","title":"Pre-trained Token-replaced Detection Model as Few-shot Learner","date":"2022-03-07","arxiv_id":"2203.03235","n_code_links":1,"syntology":null},{"paper":"/paper/divide-and-conquer-text-semantic-matching-1","slug":"divide-and-conquer-text-semantic-matching-1","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-03-06","arxiv_id":"2203.02898","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-neural-network-enhanced-language-models","title":"Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification","date":"2022-03-06","arxiv_id":"2203.02912","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-bert-for-audio","title":"Leveraging Pre-trained BERT for Audio Captioning","date":"2022-03-06","arxiv_id":"2203.02838","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-offensive-language-on-social","title":"Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks","date":"2022-03-04","arxiv_id":"2203.02123","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-guided-image-virtual-attribute","slug":"semantic-guided-image-virtual-attribute","title":"BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification","date":"2022-03-03","arxiv_id":"2203.01937","n_code_links":2,"syntology":null},{"paper":"/paper/discontinuous-constituency-and-bert-a-case-1","slug":"discontinuous-constituency-and-bert-a-case-1","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2022-03-02","arxiv_id":"2203.01063","n_code_links":1,"syntology":null},{"paper":"/paper/bert-lid-leveraging-bert-to-improve-spoken","slug":"bert-lid-leveraging-bert-to-improve-spoken","title":"BERT-LID: Leveraging BERT to Improve Spoken Language Identification","date":"2022-03-01","arxiv_id":"2203.00328","n_code_links":1,"syntology":null},{"paper":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-whole-word-masking-always-better-for-1","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","date":"2022-03-01","arxiv_id":"2203.00286","n_code_links":0,"syntology":null},{"paper":"/paper/the-impact-of-lexical-and-grammatical-1","slug":"the-impact-of-lexical-and-grammatical-1","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2022-02-28","arxiv_id":"2202.13972","n_code_links":2,"syntology":null},{"paper":"/paper/enhancing-legal-argument-mining-with-domain","slug":"enhancing-legal-argument-mining-with-domain","title":"Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks","date":"2022-02-27","arxiv_id":"2202.13457","n_code_links":1,"syntology":null},{"paper":null,"slug":"bi-directional-joint-neural-networks-for","title":"Bi-directional Joint Neural Networks for Intent Classification and Slot Filling","date":"2022-02-26","arxiv_id":"2202.13079","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-contrastive-learning-for-cross","title":"Multi-Level Contrastive Learning for Cross-Lingual Alignment","date":"2022-02-26","arxiv_id":"2202.13083","n_code_links":0,"syntology":null},{"paper":"/paper/apeach-attacking-pejorative-expressions-with","slug":"apeach-attacking-pejorative-expressions-with","title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","date":"2022-02-25","arxiv_id":"2202.12459","n_code_links":1,"syntology":null},{"paper":"/paper/bertvision-a-parameter-efficient-approach-for","slug":"bertvision-a-parameter-efficient-approach-for","title":"BERTVision -- A Parameter-Efficient Approach for Question Answering","date":"2022-02-24","arxiv_id":"2202.12210","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cbenge509/bertvision"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"finding-inverse-document-frequency","title":"Finding Inverse Document Frequency Information in BERT","date":"2022-02-24","arxiv_id":"2202.12191","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretraining-without-wordpieces-learning-over","title":"Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words","date":"2022-02-24","arxiv_id":"2202.12142","n_code_links":0,"syntology":null},{"paper":"/paper/probing-bert-s-priors-with-serial","slug":"probing-bert-s-priors-with-serial","title":"Probing BERT's priors with serial reproduction chains","date":"2022-02-24","arxiv_id":"2202.12226","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["taka-yamakoshi/telephonegame"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sky-computing-accelerating-geo-distributed","slug":"sky-computing-accelerating-geo-distributed","title":"Sky Computing: Accelerating Geo-distributed Computing in Federated Learning","date":"2022-02-24","arxiv_id":"2202.11836","n_code_links":1,"syntology":null},{"paper":null,"slug":"trimbert-tailoring-bert-for-trade-offs","title":"TrimBERT: Tailoring BERT for Trade-offs","date":"2022-02-24","arxiv_id":"2202.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-calibrator-to-improve-robustness-in","title":"Using calibrator to improve robustness in Machine Reading Comprehension","date":"2022-02-24","arxiv_id":"2202.11865","n_code_links":0,"syntology":null},{"paper":"/paper/improving-ctc-based-speech-recognition-via","slug":"improving-ctc-based-speech-recognition-via","title":"Improving CTC-based speech recognition via knowledge transferring from pre-trained language models","date":"2022-02-22","arxiv_id":"2203.03582","n_code_links":1,"syntology":null},{"paper":null,"slug":"james-job-title-mapping-with-multi-aspect","title":"JAMES: Normalizing Job Titles with Multi-Aspect Graph Embeddings and Reasoning","date":"2022-02-22","arxiv_id":"2202.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"items-from-psychometric-tests-as-training","title":"Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users","date":"2022-02-21","arxiv_id":"2202.10415","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-semantic-embeddings-for-ontology","slug":"contextual-semantic-embeddings-for-ontology","title":"Contextual Semantic Embeddings for Ontology Subsumption Prediction","date":"2022-02-20","arxiv_id":"2202.09791","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-transformers-use-variable-binding","title":"Do Transformers know symbolic rules, and would we know if they did?","date":"2022-02-19","arxiv_id":"2203.00162","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-construct-validity-of-text","slug":"evaluating-the-construct-validity-of-text","title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions","date":"2022-02-18","arxiv_id":"2202.09166","n_code_links":1,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","slug":"sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["muennighoff/sgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"when-bert-meets-quantum-temporal-convolution","title":"When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing","date":"2022-02-17","arxiv_id":"2203.03550","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-pretraining-on-graphs-taxonomy","slug":"a-survey-of-pretraining-on-graphs-taxonomy","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","date":"2022-02-16","arxiv_id":"2202.07893","n_code_links":3,"syntology":null},{"paper":null,"slug":"no-one-left-behind-inclusive-federated","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","date":"2022-02-16","arxiv_id":"2202.08036","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nlp-task-effectiveness-of-long-range","title":"The NLP Task Effectiveness of Long-Range Transformers","date":"2022-02-16","arxiv_id":"2202.07856","n_code_links":0,"syntology":null},{"paper":null,"slug":"blue-at-memotion-2-0-2022-you-have-my-image","title":"BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer","date":"2022-02-15","arxiv_id":"2202.07543","n_code_links":0,"syntology":null},{"paper":"/paper/one-configuration-to-rule-them-all-towards","slug":"one-configuration-to-rule-them-all-towards","title":"One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization","date":"2022-02-15","arxiv_id":"2202.07631","n_code_links":1,"syntology":null},{"paper":"/paper/tomayto-tomahto-beyond-token-level-answer","slug":"tomayto-tomahto-beyond-token-level-answer","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","date":"2022-02-15","arxiv_id":"2202.07654","n_code_links":1,"syntology":null},{"paper":null,"slug":"toxic-comments-hunter-score-severity-of-toxic","title":"Toxic Comments Hunter : Score Severity of Toxic Comments","date":"2022-02-15","arxiv_id":"2203.03548","n_code_links":0,"syntology":null},{"paper":null,"slug":"punctuation-restoration-in-swedish-through","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","date":"2022-02-14","arxiv_id":"2202.06769","n_code_links":0,"syntology":null},{"paper":null,"slug":"userbert-modeling-long-and-short-term-user","title":"UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision","date":"2022-02-14","arxiv_id":"2202.07605","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessment-of-contextualised-representations","title":"Assessment of contextualised representations in detecting outcome phrases in clinical trials","date":"2022-02-13","arxiv_id":"2203.03547","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-issue-classifier-a-transfer","slug":"automatic-issue-classifier-a-transfer","title":"Automatic Issue Classifier: A Transfer Learning Framework for Classifying Issue Reports","date":"2022-02-12","arxiv_id":"2202.06149","n_code_links":1,"syntology":null},{"paper":"/paper/maximizing-communication-efficiency-for-large","slug":"maximizing-communication-efficiency-for-large","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","date":"2022-02-12","arxiv_id":"2202.06009","n_code_links":1,"syntology":null},{"paper":"/paper/white-box-attacks-on-hate-speech-bert","slug":"white-box-attacks-on-hate-speech-bert","title":"White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense","date":"2022-02-11","arxiv_id":"2202.05778","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-framework-for-product","title":"A Multi-task Learning Framework for Product Ranking with BERT","date":"2022-02-10","arxiv_id":"2202.05317","n_code_links":0,"syntology":null},{"paper":null,"slug":"slovene-superglue-benchmark-translation-and","title":"Slovene SuperGLUE Benchmark: Translation and Evaluation","date":"2022-02-10","arxiv_id":"2202.04994","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-open-domain-question-answering-systems","title":"Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?","date":"2022-02-09","arxiv_id":"2202.04306","n_code_links":0,"syntology":null},{"paper":null,"slug":"merit-based-fusion-of-nlp-techniques-for","title":"Social Media as an Instant Source of Feedback on Water Quality","date":"2022-02-09","arxiv_id":"2202.04462","n_code_links":0,"syntology":null},{"paper":"/paper/pnlp-mixer-an-efficient-all-mlp-architecture","slug":"pnlp-mixer-an-efficient-all-mlp-architecture","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","date":"2022-02-09","arxiv_id":"2202.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-language-models-learn-position-role","title":"Do Language Models Learn Position-Role Mappings?","date":"2022-02-08","arxiv_id":"2202.03611","n_code_links":0,"syntology":null},{"paper":"/paper/histbert-a-pre-trained-language-model-for","slug":"histbert-a-pre-trained-language-model-for","title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","date":"2022-02-08","arxiv_id":"2202.03612","n_code_links":1,"syntology":null},{"paper":null,"slug":"logical-reasoning-for-task-oriented-dialogue","title":"Logical Reasoning for Task Oriented Dialogue Systems","date":"2022-02-08","arxiv_id":"2202.04161","n_code_links":0,"syntology":null},{"paper":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ofa-sys/ofa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-natural-language-processing-models","slug":"evaluating-natural-language-processing-models","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","date":"2022-02-06","arxiv_id":"2202.02842","n_code_links":1,"syntology":null},{"paper":null,"slug":"classification-on-sentence-embeddings-for","title":"Classification on Sentence Embeddings for Legal Assistance","date":"2022-02-05","arxiv_id":"2202.02639","n_code_links":0,"syntology":null},{"paper":null,"slug":"stonkbert-can-language-models-predict-medium","title":"StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements?","date":"2022-02-04","arxiv_id":"2202.02268","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-attention-for-language-models","slug":"temporal-attention-for-language-models","title":"Temporal Attention for Language Models","date":"2022-02-04","arxiv_id":"2202.02093","n_code_links":1,"syntology":null},{"paper":null,"slug":"asr-aware-end-to-end-neural-diarization","title":"ASR-Aware End-to-end Neural Diarization","date":"2022-02-02","arxiv_id":"2202.01286","n_code_links":0,"syntology":null},{"paper":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","n_code_links":0,"syntology":null},{"paper":null,"slug":"rescorebert-discriminative-speech-recognition","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","date":"2022-02-02","arxiv_id":"2202.01094","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-training-of-neural-networks-using","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","date":"2022-02-02","arxiv_id":"2202.00980","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-flexible-clustering-pipeline-for-mining","title":"An Adaptive Deep Clustering Pipeline to Inform Text Labeling at Scale","date":"2022-02-01","arxiv_id":"2202.01211","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semi-supervised-deep-clustering-pipeline","title":"A Semi-Supervised Deep Clustering Pipeline for Mining Intentions From Texts","date":"2022-02-01","arxiv_id":"2202.00802","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bert-based-query-by-document","title":"Improving BERT-based Query-by-Document Retrieval with Multi-Task Optimization","date":"2022-02-01","arxiv_id":"2202.00373","n_code_links":0,"syntology":null},{"paper":"/paper/regression-transformer-concurrent-conditional","slug":"regression-transformer-concurrent-conditional","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","date":"2022-02-01","arxiv_id":"2202.01338","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/regression-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-based-models-of-text","title":"Transformer-based Models of Text Normalization for Speech Applications","date":"2022-02-01","arxiv_id":"2202.00153","n_code_links":0,"syntology":null}],"record_sha256":"de05237c086b94b7bf3f96f10368a1c1f8c702c348337341f9dbe654e082f397","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}