{"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/attention-dropout/papers/95","list_of":"/method/attention-dropout","method":"Attention Dropout","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":95,"pages_in_order":109,"rows_per_page":100,"rows":[9401,9500],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"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/attention-dropout","prev":"/method/attention-dropout/papers/94","next":"/method/attention-dropout/papers/96","papers":[{"paper":null,"slug":"sjtu-nict-s-supervised-and-unsupervised","title":"SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task","date":"2020-10-11","arxiv_id":"2010.05122","n_code_links":0,"syntology":null},{"paper":"/paper/smyrf-efficient-attention-using-asymmetric","slug":"smyrf-efficient-attention-using-asymmetric","title":"SMYRF: Efficient Attention using Asymmetric Clustering","date":"2020-10-11","arxiv_id":"2010.05315","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["giannisdaras/smyrf"],"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":["unlocated"]}}},{"paper":"/paper/unsupervised-distillation-of-syntactic","slug":"unsupervised-distillation-of-syntactic","title":"Unsupervised Distillation of Syntactic Information from Contextualized Word Representations","date":"2020-10-11","arxiv_id":"2010.05265","n_code_links":1,"syntology":null},{"paper":"/paper/automated-concatenation-of-embeddings-for-1","slug":"automated-concatenation-of-embeddings-for-1","title":"Automated Concatenation of Embeddings for Structured Prediction","date":"2020-10-10","arxiv_id":"2010.05006","n_code_links":2,"syntology":null},{"paper":null,"slug":"compressing-transformer-based-semantic","title":"Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings","date":"2020-10-10","arxiv_id":"2010.05002","n_code_links":0,"syntology":null},{"paper":null,"slug":"information-extraction-from-swedish-medical","title":"Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder","date":"2020-10-10","arxiv_id":"2010.04897","n_code_links":0,"syntology":null},{"paper":"/paper/second-order-neural-dependency-parsing-with","slug":"second-order-neural-dependency-parsing-with","title":"Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training","date":"2020-10-10","arxiv_id":"2010.05003","n_code_links":1,"syntology":null},{"paper":"/paper/tag-recommendation-for-online-q-a-communities","slug":"tag-recommendation-for-online-q-a-communities","title":"Tag Recommendation for Online Q&A Communities based on BERT Pre-Training Technique","date":"2020-10-10","arxiv_id":"2010.04971","n_code_links":1,"syntology":null},{"paper":"/paper/grid-tagging-scheme-for-aspect-oriented-fine","slug":"grid-tagging-scheme-for-aspect-oriented-fine","title":"Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction","date":"2020-10-09","arxiv_id":"2010.04640","n_code_links":3,"syntology":null},{"paper":"/paper/nutcracker-at-wnut-2020-task-2-robustly","slug":"nutcracker-at-wnut-2020-task-2-robustly","title":"NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training","date":"2020-10-09","arxiv_id":"2010.04335","n_code_links":1,"syntology":null},{"paper":null,"slug":"style-attuned-pre-training-and-parameter","title":"Style Attuned Pre-training and Parameter Efficient Fine-tuning for Spoken Language Understanding","date":"2020-10-09","arxiv_id":"2010.04355","n_code_links":0,"syntology":null},{"paper":"/paper/toxic-language-detection-in-social-media-for","slug":"toxic-language-detection-in-social-media-for","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","date":"2020-10-09","arxiv_id":"2010.04543","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-generation-of-reviews-of-scientific","slug":"automatic-generation-of-reviews-of-scientific","title":"Automatic generation of reviews of scientific papers","date":"2020-10-08","arxiv_id":"2010.04147","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-meets-projective-clustering-1","title":"Deep Learning Meets Projective Clustering","date":"2020-10-08","arxiv_id":"2010.04290","n_code_links":0,"syntology":null},{"paper":"/paper/discriminatively-tuned-generative-classifiers","slug":"discriminatively-tuned-generative-classifiers","title":"Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference","date":"2020-10-08","arxiv_id":"2010.03760","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-attention-mechanism-with-query","title":"Improving Attention Mechanism with Query-Value Interaction","date":"2020-10-08","arxiv_id":"2010.03766","n_code_links":0,"syntology":null},{"paper":"/paper/infusing-disease-knowledge-into-bert-for","slug":"infusing-disease-knowledge-into-bert-for","title":"Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition","date":"2020-10-08","arxiv_id":"2010.03746","n_code_links":1,"syntology":null},{"paper":"/paper/injecting-word-information-with-multi-level","slug":"injecting-word-information-with-multi-level","title":"Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding","date":"2020-10-08","arxiv_id":"2010.03903","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-unpaired-text-data-for-training","title":"Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems","date":"2020-10-08","arxiv_id":"2010.04284","n_code_links":0,"syntology":null},{"paper":null,"slug":"masked-elmo-an-evolution-of-elmo-towards","title":"Masked ELMo: An evolution of ELMo towards fully contextual RNN language models","date":"2020-10-08","arxiv_id":"2010.04302","n_code_links":0,"syntology":null},{"paper":"/paper/parade-a-new-dataset-for-paraphrase","slug":"parade-a-new-dataset-for-paraphrase","title":"PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge","date":"2020-10-08","arxiv_id":"2010.03725","n_code_links":1,"syntology":null},{"paper":"/paper/textsettr-label-free-text-style-extraction-1","slug":"textsettr-label-free-text-style-extraction-1","title":"TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling","date":"2020-10-08","arxiv_id":"2010.03802","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-deep-learning-and-string-kernels","title":"Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets","date":"2020-10-07","arxiv_id":"2010.03614","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-fine-grained-cross-lingual-semantic","slug":"detecting-fine-grained-cross-lingual-semantic","title":"Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank","date":"2020-10-07","arxiv_id":"2010.03662","n_code_links":1,"syntology":null},{"paper":null,"slug":"dipair-fast-and-accurate-distillation-for","title":"DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling","date":"2020-10-07","arxiv_id":"2010.03099","n_code_links":0,"syntology":null},{"paper":null,"slug":"elmo-and-bert-in-semantic-change-detection","title":"ELMo and BERT in semantic change detection for Russian","date":"2020-10-07","arxiv_id":"2010.03481","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-transformers-with-approximate-1","slug":"optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","n_code_links":1,"syntology":null},{"paper":"/paper/where-are-the-facts-searching-for-fact","slug":"where-are-the-facts-searching-for-fact","title":"Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News","date":"2020-10-07","arxiv_id":"2010.03159","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["nguyenvo09/EMNLP2020"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/why-do-you-think-that-exploring-faithful","slug":"why-do-you-think-that-exploring-faithful","title":"Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision","date":"2020-10-07","arxiv_id":"2010.03384","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-individual-neurons-in-pre-trained","slug":"analyzing-individual-neurons-in-pre-trained","title":"Analyzing Individual Neurons in Pre-trained Language Models","date":"2020-10-06","arxiv_id":"2010.02695","n_code_links":1,"syntology":null},{"paper":"/paper/bert-knows-punta-cana-is-not-just-beautiful","slug":"bert-knows-punta-cana-is-not-just-beautiful","title":"BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations","date":"2020-10-06","arxiv_id":"2010.02686","n_code_links":1,"syntology":null},{"paper":"/paper/converting-the-point-of-view-of-messages","slug":"converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","n_code_links":2,"syntology":null},{"paper":"/paper/cross-lingual-text-classification-with","slug":"cross-lingual-text-classification-with","title":"Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher","date":"2020-10-06","arxiv_id":"2010.02562","n_code_links":1,"syntology":null},{"paper":"/paper/do-explicit-alignments-robustly-improve","slug":"do-explicit-alignments-robustly-improve","title":"Do Explicit Alignments Robustly Improve Multilingual Encoders?","date":"2020-10-06","arxiv_id":"2010.02537","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-bert-s-sensitivity-to-lexical-cues","slug":"exploring-bert-s-sensitivity-to-lexical-cues","title":"Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming","date":"2020-10-06","arxiv_id":"2010.03010","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 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) · 1 unverified","official":{"repos":["kanishkamisra/emnlp-bert-priming"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-efficient-neural-ranking-models","slug":"improving-efficient-neural-ranking-models","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","date":"2020-10-06","arxiv_id":"2010.02666","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-behavioral-hypotheses-for-query","title":"Incorporating Behavioral Hypotheses for Query Generation","date":"2020-10-06","arxiv_id":"2010.02667","n_code_links":0,"syntology":null},{"paper":"/paper/intrinsic-probing-through-dimension-selection","slug":"intrinsic-probing-through-dimension-selection","title":"Intrinsic Probing through Dimension Selection","date":"2020-10-06","arxiv_id":"2010.02812","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 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) · 1 unverified","official":{"repos":["rycolab/intrinsic-probing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/investigating-african-american-vernacular","slug":"investigating-african-american-vernacular","title":"Investigating African-American Vernacular English in Transformer-Based Text Generation","date":"2020-10-06","arxiv_id":"2010.02510","n_code_links":1,"syntology":null},{"paper":null,"slug":"legal-bert-the-muppets-straight-out-of-law","title":"LEGAL-BERT: The Muppets straight out of Law School","date":"2020-10-06","arxiv_id":"2010.02559","n_code_links":0,"syntology":null},{"paper":"/paper/neural-mask-generator-learning-to-generate","slug":"neural-mask-generator-learning-to-generate","title":"Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation","date":"2020-10-06","arxiv_id":"2010.02705","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-interplay-between-fine-tuning-and","title":"On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers","date":"2020-10-06","arxiv_id":"2010.02616","n_code_links":0,"syntology":null},{"paper":"/paper/poison-attacks-against-text-datasets-with","slug":"poison-attacks-against-text-datasets-with","title":"Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder","date":"2020-10-06","arxiv_id":"2010.02684","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alvinchangw/CARA_EMNLP2020"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scene-graph-modification-based-on-natural","slug":"scene-graph-modification-based-on-natural","title":"Scene Graph Modification Based on Natural Language Commands","date":"2020-10-06","arxiv_id":"2010.02591","n_code_links":1,"syntology":null},{"paper":"/paper/the-multilingual-amazon-reviews-corpus","slug":"the-multilingual-amazon-reviews-corpus","title":"The Multilingual Amazon Reviews Corpus","date":"2020-10-06","arxiv_id":"2010.02573","n_code_links":1,"syntology":null},{"paper":"/paper/genaug-data-augmentation-for-finetuning-text","slug":"genaug-data-augmentation-for-finetuning-text","title":"GenAug: Data Augmentation for Finetuning Text Generators","date":"2020-10-05","arxiv_id":"2010.01794","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-effective-is-task-agnostic-data","title":"How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?","date":"2020-10-05","arxiv_id":"2010.01764","n_code_links":0,"syntology":null},{"paper":"/paper/improving-amr-parsing-with-sequence-to","slug":"improving-amr-parsing-with-sequence-to","title":"Improving AMR Parsing with Sequence-to-Sequence Pre-training","date":"2020-10-05","arxiv_id":"2010.01771","n_code_links":1,"syntology":null},{"paper":"/paper/infobert-improving-robustness-of-language-1","slug":"infobert-improving-robustness-of-language-1","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","date":"2020-10-05","arxiv_id":"2010.02329","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AI-secure/InfoBERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"linguistic-profiling-of-a-neural-language","title":"Linguistic Profiling of a Neural Language Model","date":"2020-10-05","arxiv_id":"2010.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixup-transfomer-dynamic-data-augmentation","title":"Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks","date":"2020-10-05","arxiv_id":"2010.02394","n_code_links":0,"syntology":null},{"paper":null,"slug":"pair-planning-and-iterative-refinement-in-pre","title":"PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation","date":"2020-10-05","arxiv_id":"2010.02301","n_code_links":0,"syntology":null},{"paper":"/paper/pareto-probing-trading-off-accuracy-for","slug":"pareto-probing-trading-off-accuracy-for","title":"Pareto Probing: Trading Off Accuracy for Complexity","date":"2020-10-05","arxiv_id":"2010.02180","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["rycolab/pareto-probing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/pmi-masking-principled-masking-of-correlated-1","slug":"pmi-masking-principled-masking-of-correlated-1","title":"PMI-Masking: Principled masking of correlated spans","date":"2020-10-05","arxiv_id":"2010.01825","n_code_links":1,"syntology":null},{"paper":"/paper/pruning-redundant-mappings-in-transformer","slug":"pruning-redundant-mappings-in-transformer","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","date":"2020-10-05","arxiv_id":"2010.01791","n_code_links":1,"syntology":null},{"paper":null,"slug":"pum-at-semeval-2020-task-12-aggregation-of","title":"PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition","date":"2020-10-05","arxiv_id":"2010.01897","n_code_links":0,"syntology":null},{"paper":"/paper/self-training-improves-pre-training-for","slug":"self-training-improves-pre-training-for","title":"Self-training Improves Pre-training for Natural Language Understanding","date":"2020-10-05","arxiv_id":"2010.02194","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-reference-free-summary-quality","slug":"unsupervised-reference-free-summary-quality","title":"Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning","date":"2020-10-05","arxiv_id":"2010.01781","n_code_links":1,"syntology":null},{"paper":"/paper/x-srl-a-parallel-cross-lingual-semantic-role","slug":"x-srl-a-parallel-cross-lingual-semantic-role","title":"X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset","date":"2020-10-05","arxiv_id":"2010.01998","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-study-on-large-scale-multi-label","slug":"an-empirical-study-on-large-scale-multi-label","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","date":"2020-10-04","arxiv_id":"2010.01653","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iliaschalkidis/lmtc-eurlex57k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/inquisitive-question-generation-for-high","slug":"inquisitive-question-generation-for-high","title":"Inquisitive Question Generation for High Level Text Comprehension","date":"2020-10-04","arxiv_id":"2010.01657","n_code_links":1,"syntology":null},{"paper":"/paper/on-losses-for-modern-language-models","slug":"on-losses-for-modern-language-models","title":"On Losses for Modern Language Models","date":"2020-10-04","arxiv_id":"2010.01694","n_code_links":1,"syntology":null},{"paper":"/paper/mining-knowledge-for-natural-language","slug":"mining-knowledge-for-natural-language","title":"Mining Knowledge for Natural Language Inference from Wikipedia Categories","date":"2020-10-03","arxiv_id":"2010.01239","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":["ZeweiChu/WikiNLI"],"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":"personality-trait-detection-using-bagged-svm","title":"Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles","date":"2020-10-03","arxiv_id":"2010.01309","n_code_links":0,"syntology":null},{"paper":"/paper/cost-effective-selection-of-pretraining-data","slug":"cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","arxiv_id":"2010.01150","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-tail-zero-and-few-shot-learning-via","title":"Data-Efficient Pretraining via Contrastive Self-Supervision","date":"2020-10-02","arxiv_id":"2010.01061","n_code_links":0,"syntology":null},{"paper":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","n_code_links":9,"syntology":{"ran":3,"of":10,"n_ran_checked":3,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/multicqa-zero-shot-transfer-of-self","slug":"multicqa-zero-shot-transfer-of-self","title":"MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale","date":"2020-10-02","arxiv_id":"2010.00980","n_code_links":1,"syntology":null},{"paper":"/paper/stil-simultaneous-slot-filling-translation","slug":"stil-simultaneous-slot-filling-translation","title":"STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++","date":"2020-10-02","arxiv_id":"2010.00760","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-the-text-analysis-of-privacy","title":"Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling","date":"2020-10-01","arxiv_id":"2010.00678","n_code_links":0,"syntology":null},{"paper":"/paper/colake-contextualized-language-and-knowledge","slug":"colake-contextualized-language-and-knowledge","title":"CoLAKE: Contextualized Language and Knowledge Embedding","date":"2020-10-01","arxiv_id":"2010.00309","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 0 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) · 1 unverified","official":{"repos":["txsun1997/CoLAKE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-white-supremacist-hate-speech-using","title":"Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERT","date":"2020-10-01","arxiv_id":"2010.00357","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-multilingual-bert-for-estonian","title":"Evaluating Multilingual BERT for Estonian","date":"2020-10-01","arxiv_id":"2010.00454","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","n_code_links":2,"syntology":null},{"paper":null,"slug":"rrf102-meeting-the-trec-covid-challenge-with","title":"RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble","date":"2020-10-01","arxiv_id":"2010.00200","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-tables-with-intermediate-pre","slug":"understanding-tables-with-intermediate-pre","title":"Understanding tables with intermediate pre-training","date":"2020-10-01","arxiv_id":"2010.00571","n_code_links":1,"syntology":null},{"paper":"/paper/a-tale-of-two-linkings-dynamically-gating","slug":"a-tale-of-two-linkings-dynamically-gating","title":"A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing","date":"2020-09-30","arxiv_id":"2009.14809","n_code_links":1,"syntology":null},{"paper":"/paper/a-vietnamese-dataset-for-evaluating-machine","slug":"a-vietnamese-dataset-for-evaluating-machine","title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","date":"2020-09-30","arxiv_id":"2009.14725","n_code_links":0,"syntology":null},{"paper":null,"slug":"auber-automated-bert-regularization","title":"AUBER: Automated BERT Regularization","date":"2020-09-30","arxiv_id":"2009.14409","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-monolingual-and-cross-lingual","slug":"bert-for-monolingual-and-cross-lingual","title":"BERT for Monolingual and Cross-Lingual Reverse Dictionary","date":"2020-09-30","arxiv_id":"2009.14790","n_code_links":1,"syntology":null},{"paper":null,"slug":"pea-kd-parameter-efficient-and-accurate","title":"Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT","date":"2020-09-30","arxiv_id":"2009.14822","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-distillation-on-intermediate","slug":"contrastive-distillation-on-intermediate","title":"Contrastive Distillation on Intermediate Representations for Language Model Compression","date":"2020-09-29","arxiv_id":"2009.14167","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 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) · 2 unverified","official":{"repos":["intersun/CoDIR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cross-lingual-alignment-methods-for","title":"Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study","date":"2020-09-29","arxiv_id":"2009.14304","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-twitter-to-traffic-predictor-next-day","title":"From Twitter to Traffic Predictor: Next-Day Morning Traffic Prediction Using Social Media Data","date":"2020-09-29","arxiv_id":"2009.13794","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-prediction-using-limited-twitter-data","title":"Gender prediction using limited Twitter Data","date":"2020-09-29","arxiv_id":"2010.02005","n_code_links":0,"syntology":null},{"paper":"/paper/hint3-raising-the-bar-for-intent-detection-in","slug":"hint3-raising-the-bar-for-intent-detection-in","title":"HINT3: Raising the bar for Intent Detection in the Wild","date":"2020-09-29","arxiv_id":"2009.13833","n_code_links":1,"syntology":null},{"paper":null,"slug":"map-a-matrix-based-prediction-approach-to","title":"MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension","date":"2020-09-29","arxiv_id":"2009.14348","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-retrieval-for-question-answering-with","title":"Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation","date":"2020-09-29","arxiv_id":"2009.13815","n_code_links":0,"syntology":null},{"paper":null,"slug":"test-positive-at-w-nut-2020-shared-task-3","title":"TEST_POSITIVE at W-NUT 2020 Shared Task-3: Joint Event Multi-task Learning for Slot Filling in Noisy Text","date":"2020-09-29","arxiv_id":"2009.14262","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-design-and-implementation-of-language","title":"The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning","date":"2020-09-29","arxiv_id":"2009.13984","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision","slug":"visually-grounded-planning-without-vision","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-09-29","arxiv_id":"2009.14259","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cognitiveailab/alfred-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-simple-and-efficient-ensemble-classifier","title":"A Simple and Efficient Ensemble Classifier Combining Multiple Neural Network Models on Social Media Datasets in Vietnamese","date":"2020-09-28","arxiv_id":"2009.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-multi-model-inference-by-merging","title":"Accelerating Multi-Model Inference by Merging DNNs of Different Weights","date":"2020-09-28","arxiv_id":"2009.13062","n_code_links":0,"syntology":null},{"paper":"/paper/dialoglue-a-natural-language-understanding","slug":"dialoglue-a-natural-language-understanding","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","date":"2020-09-28","arxiv_id":"2009.13570","n_code_links":1,"syntology":null},{"paper":null,"slug":"fancy-man-lauches-zippo-at-wnut-2020-shared","title":"Fancy Man Lauches Zippo at WNUT 2020 Shared Task-1: A Bert Case Model for Wet Lab Entity Extraction","date":"2020-09-28","arxiv_id":"2009.12997","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-aware-procedural-text-understanding","title":"Knowledge-Aware Procedural Text Understanding with Multi-Stage Training","date":"2020-09-28","arxiv_id":"2009.13199","n_code_links":0,"syntology":null},{"paper":null,"slug":"pin-a-novel-parallel-interactive-network-for","title":"PIN: A Novel Parallel Interactive Network for Spoken Language Understanding","date":"2020-09-28","arxiv_id":"2009.13431","n_code_links":0,"syntology":null},{"paper":"/paper/ternarybert-distillation-aware-ultra-low-bit","slug":"ternarybert-distillation-aware-ultra-low-bit","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","date":"2020-09-27","arxiv_id":"2009.12812","n_code_links":5,"syntology":null},{"paper":null,"slug":"what-does-it-mean-to-be-language-agnostic","title":"What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties","date":"2020-09-27","arxiv_id":"2009.12862","n_code_links":0,"syntology":null}],"record_sha256":"196321cb10c58289a9c2db281582276ad1bf7e21ece15fadd47ae916f2393226","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}