{"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/weight-decay/papers/97","list_of":"/method/weight-decay","method":"Weight 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":97,"pages_in_order":108,"rows_per_page":100,"rows":[9601,9700],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/96","next":"/method/weight-decay/papers/98","papers":[{"paper":"/paper/klej-comprehensive-benchmark-for-polish","slug":"klej-comprehensive-benchmark-for-polish","title":"KLEJ: Comprehensive Benchmark for Polish Language Understanding","date":"2020-05-01","arxiv_id":"2005.00630","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":["allegro/klejbenchmark-baselines"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"massive-vs-curated-embeddings-for-low","title":"Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yor\\`ub\\'a and Twi","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-corpus-creation-for-multilingual","title":"Multilingual Corpus Creation for Multilingual Semantic Similarity Task","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/neural-symbolic-reader-scalable-integration","slug":"neural-symbolic-reader-scalable-integration","title":"Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"one-classifier-for-all-ambiguous-words","title":"One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"parsing-as-tagging","title":"Parsing as Tagging","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pointer-constrained-text-generation-via","slug":"pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","arxiv_id":"2005.00558","n_code_links":1,"syntology":{"ran":11,"of":18,"n_ran_checked":6,"n_instrument":5,"unverified":7,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["dreasysnail/POINTER"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"probing-text-models-for-common-ground-with","title":"Probing Contextual Language Models for Common Ground with Visual Representations","date":"2020-05-01","arxiv_id":"2005.00619","n_code_links":0,"syntology":null},{"paper":"/paper/scirex-a-challenge-dataset-for-document-level","slug":"scirex-a-challenge-dataset-for-document-level","title":"SciREX: A Challenge Dataset for Document-Level Information Extraction","date":"2020-05-01","arxiv_id":"2005.00512","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/SciREX"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scmhl5-at-trac-2-shared-task-on-aggression","title":"Scmhl5 at TRAC-2 Shared Task on Aggression Identification: Bert Based Ensemble Learning Approach","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sibert-enhanced-chinese-pre-trained-language","slug":"sibert-enhanced-chinese-pre-trained-language","title":"SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"termeval-2020-taln-ls2n-system-for-automatic","title":"TermEval 2020: TALN-LS2N System for Automatic Term Extraction","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"text-categorization-for-conflict-event","title":"Text Categorization for Conflict Event Annotation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tf-idf-character-n-grams-versus-word","title":"TF-IDF Character N-grams versus Word Embedding-based Models for Fine-grained Event Classification: A Preliminary Study","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-applied-to-text","title":"Transfer learning applied to text classification in Spanish radiological reports","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-generalization-in-recurrent","title":"Understanding Generalization in Recurrent Neural Networks","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-user-utterances-in-a-dialog","title":"Understanding User Utterances in a Dialog System for Caregiving","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-bert-plays-the-lottery-all-tickets-are","title":"When BERT Plays the Lottery, All Tickets Are Winning","date":"2020-05-01","arxiv_id":"2005.00561","n_code_links":0,"syntology":null},{"paper":"/paper/a-focused-study-to-compare-arabic-pre","slug":"a-focused-study-to-compare-arabic-pre","title":"An Empirical Study of Pre-trained Transformers for Arabic Information Extraction","date":"2020-04-30","arxiv_id":"2004.14519","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-matter-of-framing-the-impact-of-linguistic","title":"A Matter of Framing: The Impact of Linguistic Formalism on Probing Results","date":"2020-04-30","arxiv_id":"2004.14999","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriched-pre-trained-transformers-for-joint","title":"Enriched Pre-trained Transformers for Joint Slot Filling and Intent Detection","date":"2020-04-30","arxiv_id":"2004.14848","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-contextualized-neural-language","slug":"exploring-contextualized-neural-language","title":"Exploring Contextualized Neural Language Models for Temporal Dependency Parsing","date":"2020-04-30","arxiv_id":"2004.14577","n_code_links":1,"syntology":null},{"paper":"/paper/how-do-decisions-emerge-across-layers-in","slug":"how-do-decisions-emerge-across-layers-in","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","date":"2020-04-30","arxiv_id":"2004.14992","n_code_links":2,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["nicola-decao/diffmask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"interpretable-entity-representations-through","title":"Interpretable Entity Representations through Large-Scale Typing","date":"2020-04-30","arxiv_id":"2005.00147","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-transferability-in-pretrained","slug":"investigating-transferability-in-pretrained","title":"Investigating Transferability in Pretrained Language Models","date":"2020-04-30","arxiv_id":"2004.14975","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":["dgiova/bert-lm-transferability"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/look-at-the-first-sentence-position-bias-in","slug":"look-at-the-first-sentence-position-bias-in","title":"Look at the First Sentence: Position Bias in Question Answering","date":"2020-04-30","arxiv_id":"2004.14602","n_code_links":1,"syntology":null},{"paper":"/paper/mad-x-an-adapter-based-framework-for-multi","slug":"mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","n_code_links":3,"syntology":null},{"paper":"/paper/modular-representation-underlies-systematic","slug":"modular-representation-underlies-systematic","title":"Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation","date":"2020-04-30","arxiv_id":"2004.14623","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-evaluation-of-contextual-embeddings","title":"Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings","date":"2020-04-30","arxiv_id":"2004.15001","n_code_links":0,"syntology":null},{"paper":"/paper/perturbed-masking-parameter-free-probing-for","slug":"perturbed-masking-parameter-free-probing-for","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","date":"2020-04-30","arxiv_id":"2004.14786","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LividWo/Perturbed-Masking"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/plotmachines-outline-conditioned-generation","slug":"plotmachines-outline-conditioned-generation","title":"PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking","date":"2020-04-30","arxiv_id":"2004.14967","n_code_links":2,"syntology":{"ran":5,"of":11,"n_ran_checked":5,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hrashkin/plotmachines"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robust-question-answering-through-sub-part","title":"Robust Question Answering Through Sub-part Alignment","date":"2020-04-30","arxiv_id":"2004.14648","n_code_links":0,"syntology":null},{"paper":"/paper/segabert-pre-training-of-segment-aware-bert","slug":"segabert-pre-training-of-segment-aware-bert","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","date":"2020-04-30","arxiv_id":"2004.14996","n_code_links":1,"syntology":null},{"paper":"/paper/textat-adversarial-training-for-natural","slug":"textat-adversarial-training-for-natural","title":"TAVAT: Token-Aware Virtual Adversarial Training for Language Understanding","date":"2020-04-30","arxiv_id":"2004.14543","n_code_links":1,"syntology":null},{"paper":"/paper/universal-dependencies-according-to-bert-both","slug":"universal-dependencies-according-to-bert-both","title":"Universal Dependencies according to BERT: both more specific and more general","date":"2020-04-30","arxiv_id":"2004.14620","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["Tom556/BERTHeadEnsembles"],"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/wic-tsv-an-evaluation-benchmark-for-target","slug":"wic-tsv-an-evaluation-benchmark-for-target","title":"WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context","date":"2020-04-30","arxiv_id":"2004.15016","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-supervised-word-alignment-method-based-on","title":"A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT","date":"2020-04-29","arxiv_id":"2004.14516","n_code_links":0,"syntology":null},{"paper":"/paper/analysing-lexical-semantic-change-with","slug":"analysing-lexical-semantic-change-with","title":"Analysing Lexical Semantic Change with Contextualised Word Representations","date":"2020-04-29","arxiv_id":"2004.14118","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["glnmario/cwr4lsc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"asking-without-telling-exploring-latent","title":"Asking without Telling: Exploring Latent Ontologies in Contextual Representations","date":"2020-04-29","arxiv_id":"2004.14513","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-text-extraction-as-reading","title":"Bilingual Text Extraction as Reading Comprehension","date":"2020-04-29","arxiv_id":"2004.14517","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-perceived-emotions-in-hurricane","slug":"detecting-perceived-emotions-in-hurricane","title":"Detecting Perceived Emotions in Hurricane Disasters","date":"2020-04-29","arxiv_id":"2004.14299","n_code_links":1,"syntology":null},{"paper":"/paper/distantly-supervised-neural-relation","slug":"distantly-supervised-neural-relation","title":"Distantly-Supervised Neural Relation Extraction with Side Information using BERT","date":"2020-04-29","arxiv_id":"2004.14443","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-neural-language-models-show-preferences","title":"Do Neural Language Models Show Preferences for Syntactic Formalisms?","date":"2020-04-29","arxiv_id":"2004.14096","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-slot-alignment-and-recognition-for","slug":"end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","n_code_links":3,"syntology":null},{"paper":"/paper/geppetto-carves-italian-into-a-language-model","slug":"geppetto-carves-italian-into-a-language-model","title":"GePpeTto Carves Italian into a Language Model","date":"2020-04-29","arxiv_id":"2004.14253","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-universal-representations","title":"BURT: BERT-inspired Universal Representation from Twin Structure","date":"2020-04-29","arxiv_id":"2004.13947","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-pre-trained-models-for-chinese","slug":"revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","arxiv_id":"2004.13922","n_code_links":6,"syntology":{"ran":21,"of":35,"n_ran_checked":16,"n_instrument":5,"unverified":14,"pointer_only":4,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","official":{"repos":["ymcui/MacBERT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/textattack-a-framework-for-adversarial","slug":"textattack-a-framework-for-adversarial","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","date":"2020-04-29","arxiv_id":"2005.05909","n_code_links":2,"syntology":null},{"paper":"/paper/training-curricula-for-open-domain-answer-re","slug":"training-curricula-for-open-domain-answer-re","title":"Training Curricula for Open Domain Answer Re-Ranking","date":"2020-04-29","arxiv_id":"2004.14269","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-happens-to-bert-embeddings-during-fine","title":"What Happens To BERT Embeddings During Fine-tuning?","date":"2020-04-29","arxiv_id":"2004.14448","n_code_links":0,"syntology":null},{"paper":"/paper/dombert-domain-oriented-language-model-for","slug":"dombert-domain-oriented-language-model-for","title":"DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis","date":"2020-04-28","arxiv_id":"2004.13816","n_code_links":1,"syntology":null},{"paper":null,"slug":"earl-speedup-transformer-based-rankers-with","title":"Modularized Transfomer-based Ranking Framework","date":"2020-04-28","arxiv_id":"2004.13313","n_code_links":0,"syntology":null},{"paper":null,"slug":"extending-multilingual-bert-to-low-resource","title":"Extending Multilingual BERT to Low-Resource Languages","date":"2020-04-28","arxiv_id":"2004.13640","n_code_links":0,"syntology":null},{"paper":"/paper/joint-keyphrase-chunking-and-salience-ranking","slug":"joint-keyphrase-chunking-and-salience-ranking","title":"Capturing Global Informativeness in Open Domain Keyphrase Extraction","date":"2020-04-28","arxiv_id":"2004.13639","n_code_links":2,"syntology":null},{"paper":"/paper/kungfupanda-at-semeval-2020-task-12-bert","slug":"kungfupanda-at-semeval-2020-task-12-bert","title":"Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection","date":"2020-04-28","arxiv_id":"2004.13432","n_code_links":1,"syntology":null},{"paper":"/paper/vd-bert-a-unified-vision-and-dialog","slug":"vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","date":"2020-04-28","arxiv_id":"2004.13278","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["salesforce/VD-BERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/colbert-efficient-and-effective-passage","slug":"colbert-efficient-and-effective-passage","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","date":"2020-04-27","arxiv_id":"2004.12832","n_code_links":9,"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":["stanford-futuredata/ColBERT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/colbert-using-bert-sentence-embedding-for","slug":"colbert-using-bert-sentence-embedding-for","title":"ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor","date":"2020-04-27","arxiv_id":"2004.12765","n_code_links":4,"syntology":null},{"paper":"/paper/deebert-dynamic-early-exiting-for","slug":"deebert-dynamic-early-exiting-for","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","date":"2020-04-27","arxiv_id":"2004.12993","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["castorini/deebert"],"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":["listed","official"]}}},{"paper":null,"slug":"lightpaff-a-two-stage-distillation-framework-1","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","date":"2020-04-27","arxiv_id":"2004.12817","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-importance-of-word-and-sentence","slug":"on-the-importance-of-word-and-sentence","title":"On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification","date":"2020-04-27","arxiv_id":"2004.12617","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":["HKUST-KnowComp/BMGF-RoBERTa"],"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/recall-and-learn-fine-tuning-deep-pretrained","slug":"recall-and-learn-fine-tuning-deep-pretrained","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","date":"2020-04-27","arxiv_id":"2004.12651","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-discourse-relations-in-language","title":"Assessing Discourse Relations in Language Generation from GPT-2","date":"2020-04-26","arxiv_id":"2004.12506","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-512-tokens-siamese-multi-depth","slug":"beyond-512-tokens-siamese-multi-depth","title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","date":"2020-04-26","arxiv_id":"2004.12297","n_code_links":1,"syntology":null},{"paper":null,"slug":"challenge-closed-book-science-exam-a-meta","title":"Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System","date":"2020-04-26","arxiv_id":"2004.12303","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-of-cuisines-from-sequentially","title":"Classification of Cuisines from Sequentially Structured Recipes","date":"2020-04-26","arxiv_id":"2004.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"masking-as-an-efficient-alternative-to","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","date":"2020-04-26","arxiv_id":"2004.12406","n_code_links":0,"syntology":null},{"paper":"/paper/spellgcn-incorporating-phonological-and","slug":"spellgcn-incorporating-phonological-and","title":"SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check","date":"2020-04-26","arxiv_id":"2004.14166","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-the-contextualization-of-word","title":"Quantifying the Contextualization of Word Representations with Semantic Class Probing","date":"2020-04-25","arxiv_id":"2004.12198","n_code_links":0,"syntology":null},{"paper":"/paper/a-tailored-pre-training-model-for-task","slug":"a-tailored-pre-training-model-for-task","title":"A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2020-04-24","arxiv_id":"2004.13835","n_code_links":1,"syntology":null},{"paper":"/paper/collecting-entailment-data-for-pretraining","slug":"collecting-entailment-data-for-pretraining","title":"New Protocols and Negative Results for Textual Entailment Data Collection","date":"2020-04-24","arxiv_id":"2004.11997","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualized-representations-using-textual","title":"Contextualized Representations Using Textual Encyclopedic Knowledge","date":"2020-04-24","arxiv_id":"2004.12006","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-annealing-for-informal-language","title":"Data Annealing for Informal Language Understanding Tasks","date":"2020-04-24","arxiv_id":"2004.13833","n_code_links":0,"syntology":null},{"paper":null,"slug":"pbcs-efficient-exploration-and-exploitation","title":"PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning","date":"2020-04-24","arxiv_id":"2004.11667","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistically-masked-language-model","slug":"probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","arxiv_id":"2004.11579","n_code_links":3,"syntology":{"ran":21,"of":35,"n_ran_checked":12,"n_instrument":9,"unverified":14,"pointer_only":29,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 3 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/syntactic-data-augmentation-increases","slug":"syntactic-data-augmentation-increases","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","date":"2020-04-24","arxiv_id":"2004.11999","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aatlantise/syntactic-augmentation-nli"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-inception-team-at-nsurl-2019-task-8","slug":"the-inception-team-at-nsurl-2019-task-8","title":"The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic","date":"2020-04-24","arxiv_id":"2004.11964","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-adversarial-examples-for-biomedical-nlp","title":"On Adversarial Examples for Biomedical NLP Tasks","date":"2020-04-23","arxiv_id":"2004.11157","n_code_links":0,"syntology":null},{"paper":null,"slug":"same-side-stance-classification-task","title":"Same Side Stance Classification Task: Facilitating Argument Stance Classification by Fine-tuning a BERT Model","date":"2020-04-23","arxiv_id":"2004.11163","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-attribution-interpreting","slug":"self-attention-attribution-interpreting","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","date":"2020-04-23","arxiv_id":"2004.11207","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["YRdddream/attattr"],"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":"uhh-lt-lt2-at-semeval-2020-task-12-fine","title":"UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection","date":"2020-04-23","arxiv_id":"2004.11493","n_code_links":0,"syntology":null},{"paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","slug":"yolov4-optimal-speed-and-accuracy-of-object","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","date":"2020-04-23","arxiv_id":"2004.10934","n_code_links":223,"syntology":{"ran":142,"of":184,"n_ran_checked":133,"n_instrument":9,"unverified":42,"pointer_only":21,"phrase":"142 ran (of which 0 constructed an object rather than computing a result; 133 with no instrument failure: 6 honoured, 0 violated, 127 with no contract checked; 9 where Syntology's instrument failed) · 42 unverified","official":{"repos":["AlexeyAB/darknet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"keyphrase-prediction-with-pre-trained","title":"Keyphrase Prediction With Pre-trained Language Model","date":"2020-04-22","arxiv_id":"2004.10462","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-classify-intents-and-slot-labels","title":"Learning to Classify Intents and Slot Labels Given a Handful of Examples","date":"2020-04-22","arxiv_id":"2004.10793","n_code_links":0,"syntology":null},{"paper":"/paper/residual-energy-based-models-for-text-1","slug":"residual-energy-based-models-for-text-1","title":"Residual Energy-Based Models for Text Generation","date":"2020-04-22","arxiv_id":"2004.11714","n_code_links":1,"syntology":null},{"paper":"/paper/attention-module-is-not-only-a-weight","slug":"attention-module-is-not-only-a-weight","title":"Attention is Not Only a Weight: Analyzing Transformers with Vector Norms","date":"2020-04-21","arxiv_id":"2004.10102","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gorokoba560/norm-analysis-of-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert-attack-adversarial-attack-against-bert","slug":"bert-attack-adversarial-attack-against-bert","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","date":"2020-04-21","arxiv_id":"2004.09984","n_code_links":4,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["LinyangLee/BERT-Attack","QData/TextAttack"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","unlocated"]}}},{"paper":"/paper/diet-lightweight-language-understanding-for","slug":"diet-lightweight-language-understanding-for","title":"DIET: Lightweight Language Understanding for Dialogue Systems","date":"2020-04-21","arxiv_id":"2004.09936","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["RasaHQ/DIET-paper"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"domain-guided-task-decomposition-with-self","title":"Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media","date":"2020-04-21","arxiv_id":"2004.10201","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effectiveness-of","title":"Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets","date":"2020-04-21","arxiv_id":"2004.13138","n_code_links":0,"syntology":null},{"paper":null,"slug":"mirror-ritual-an-affective-interface-for","title":"Mirror Ritual: An Affective Interface for Emotional Self-Reflection","date":"2020-04-21","arxiv_id":"2004.09685","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-cross-lingual-ability-and-language","title":"A Study of Cross-Lingual Ability and Language-specific Information in Multilingual BERT","date":"2020-04-20","arxiv_id":"2004.09205","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-training-for-large-neural","slug":"adversarial-training-for-large-neural","title":"Adversarial Training for Large Neural Language Models","date":"2020-04-20","arxiv_id":"2004.08994","n_code_links":3,"syntology":null},{"paper":"/paper/chexbert-combining-automatic-labelers-and","slug":"chexbert-combining-automatic-labelers-and","title":"CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT","date":"2020-04-20","arxiv_id":"2004.09167","n_code_links":7,"syntology":{"ran":15,"of":17,"n_ran_checked":11,"n_instrument":4,"unverified":2,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["stanfordmlgroup/CheXbert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/mpnet-masked-and-permuted-pre-training-for","slug":"mpnet-masked-and-permuted-pre-training-for","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","date":"2020-04-20","arxiv_id":"2004.09297","n_code_links":7,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/MPNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/stereoset-measuring-stereotypical-bias-in","slug":"stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","date":"2020-04-20","arxiv_id":"2004.09456","n_code_links":3,"syntology":null},{"paper":"/paper/resnest-split-attention-networks","slug":"resnest-split-attention-networks","title":"ResNeSt: Split-Attention Networks","date":"2020-04-19","arxiv_id":"2004.08955","n_code_links":36,"syntology":{"ran":28,"of":48,"n_ran_checked":25,"n_instrument":3,"unverified":20,"pointer_only":23,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 0 honoured, 0 violated, 25 with no contract checked; 3 where Syntology's instrument failed) · 20 unverified","official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/enhancing-pharmacovigilance-with-drug-reviews","slug":"enhancing-pharmacovigilance-with-drug-reviews","title":"Enhancing Pharmacovigilance with Drug Reviews and Social Media","date":"2020-04-18","arxiv_id":"2004.08731","n_code_links":1,"syntology":null},{"paper":"/paper/fast-and-accurate-deep-bidirectional-language","slug":"fast-and-accurate-deep-bidirectional-language","title":"Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning","date":"2020-04-17","arxiv_id":"2004.08097","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":["joongbo/tta"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}],"record_sha256":"fa600e53d844b4081b3154ce9fb8aadc08ebe43bbf6fcb9abb1580c2cae08e6a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}