{"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/89","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":89,"pages_in_order":109,"rows_per_page":100,"rows":[8801,8900],"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/88","next":"/method/attention-dropout/papers/90","papers":[{"paper":null,"slug":"adversarially-learning-disentangled-speech","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","date":"2021-01-30","arxiv_id":"2102.00184","n_code_links":0,"syntology":null},{"paper":null,"slug":"empathbert-a-bert-based-framework-for","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","date":"2021-01-30","arxiv_id":"2102.00272","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-how-human-correct","slug":"learning-from-how-human-correct","title":"Learning From Human Correction","date":"2021-01-30","arxiv_id":"2102.00225","n_code_links":1,"syntology":null},{"paper":null,"slug":"shuftext-a-simple-black-box-approach-to","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","date":"2021-01-30","arxiv_id":"2102.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-recognition-by-simply-fine-tuning-bert","title":"Speech Recognition by Simply Fine-tuning BERT","date":"2021-01-30","arxiv_id":"2102.00291","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-bert-based-models-for-plant","slug":"fine-tuning-bert-based-models-for-plant","title":"Fine-tuning BERT-based models for Plant Health Bulletin Classification","date":"2021-01-29","arxiv_id":"2102.00838","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthesizing-monolingual-data-for-neural","title":"Synthesizing Monolingual Data for Neural Machine Translation","date":"2021-01-29","arxiv_id":"2101.12462","n_code_links":0,"syntology":null},{"paper":"/paper/a-graph-based-relevance-matching-model-for-ad","slug":"a-graph-based-relevance-matching-model-for-ad","title":"A Graph-based Relevance Matching Model for Ad-hoc Retrieval","date":"2021-01-28","arxiv_id":"2101.11873","n_code_links":1,"syntology":null},{"paper":null,"slug":"bertau-itau-bert-for-digital-customer-service","title":"BERTaú: Itaú BERT for digital customer service","date":"2021-01-28","arxiv_id":"2101.12015","n_code_links":0,"syntology":null},{"paper":null,"slug":"korealbert-pretraining-a-lite-bert-model-for","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","date":"2021-01-27","arxiv_id":"2101.11363","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-evolution-of-syntactic-information","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","date":"2021-01-27","arxiv_id":"2101.11492","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-zero-shot-cross-lingual-transfer-in","title":"Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks","date":"2021-01-26","arxiv_id":"2101.10649","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-can-reflect-syntactic-structure-if","title":"Attention Can Reflect Syntactic Structure (If You Let It)","date":"2021-01-26","arxiv_id":"2101.10927","n_code_links":0,"syntology":null},{"paper":null,"slug":"climp-a-benchmark-for-chinese-language-model","title":"CLiMP: A Benchmark for Chinese Language Model Evaluation","date":"2021-01-26","arxiv_id":"2101.11131","n_code_links":0,"syntology":null},{"paper":"/paper/deep-subjecthood-higher-order-grammatical","slug":"deep-subjecthood-higher-order-grammatical","title":"Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11043","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-bert-and-albert-sentence","title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","date":"2021-01-26","arxiv_id":"2101.10642","n_code_links":0,"syntology":null},{"paper":"/paper/first-align-then-predict-understanding-the","slug":"first-align-then-predict-understanding-the","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11109","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-recognition-in-the-style-of","title":"Named Entity Recognition in the Style of Object Detection","date":"2021-01-26","arxiv_id":"2101.11122","n_code_links":0,"syntology":null},{"paper":null,"slug":"regulatory-compliance-through-doc2doc","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","date":"2021-01-26","arxiv_id":"2101.10726","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-approach-to-measure-semantic","title":"A Hybrid Approach to Measure Semantic Relatedness in Biomedical Concepts","date":"2021-01-25","arxiv_id":"2101.10196","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-dialog-length-matter-for-next-response","title":"Does Dialog Length matter for Next Response Selection task? An Empirical Study","date":"2021-01-24","arxiv_id":"2101.09647","n_code_links":0,"syntology":null},{"paper":"/paper/romebert-robust-training-of-multi-exit-bert","slug":"romebert-robust-training-of-multi-exit-bert","title":"RomeBERT: Robust Training of Multi-Exit BERT","date":"2021-01-24","arxiv_id":"2101.09755","n_code_links":1,"syntology":null},{"paper":"/paper/stereotype-and-skew-quantifying-gender-bias","slug":"stereotype-and-skew-quantifying-gender-bias","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","date":"2021-01-24","arxiv_id":"2101.09688","n_code_links":1,"syntology":null},{"paper":"/paper/training-multilingual-pre-trained-language","slug":"training-multilingual-pre-trained-language","title":"Training Multilingual Pre-trained Language Model with Byte-level Subwords","date":"2021-01-23","arxiv_id":"2101.09469","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-perspective-combined-recall-and-rank","title":"A multi-perspective combined recall and rank framework for Chinese procedure terminology normalization","date":"2021-01-22","arxiv_id":"2101.09101","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-transformer-model-for-detecting-arabic","title":"BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets","date":"2021-01-22","arxiv_id":"2101.09345","n_code_links":0,"syntology":null},{"paper":"/paper/drug-and-disease-interpretation-learning-with","slug":"drug-and-disease-interpretation-learning-with","title":"Drug and Disease Interpretation Learning with Biomedical Entity Representation Transformer","date":"2021-01-22","arxiv_id":"2101.09311","n_code_links":1,"syntology":null},{"paper":null,"slug":"extracting-lifestyle-factors-for-alzheimer-s","title":"Extracting Lifestyle Factors for Alzheimer's Disease from Clinical Notes Using Deep Learning with Weak Supervision","date":"2021-01-22","arxiv_id":"2101.09244","n_code_links":0,"syntology":null},{"paper":"/paper/hasocone-fire-hasoc2020-using-bert-and","slug":"hasocone-fire-hasoc2020-using-bert-and","title":"HASOCOne@FIRE-HASOC2020: Using BERT and Multilingual BERT models for Hate Speech Detection","date":"2021-01-22","arxiv_id":"2101.09007","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-pre-trained-transformers-and","title":"Multilingual Pre-Trained Transformers and Convolutional NN Classification Models for Technical Domain Identification","date":"2021-01-22","arxiv_id":"2101.09012","n_code_links":0,"syntology":null},{"paper":"/paper/the-heads-hypothesis-a-unifying-statistical","slug":"the-heads-hypothesis-a-unifying-statistical","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","date":"2021-01-22","arxiv_id":"2101.09115","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-multilingual-text-encoders-for","slug":"evaluating-multilingual-text-encoders-for","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","date":"2021-01-21","arxiv_id":"2101.08370","n_code_links":1,"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":["rlitschk/EncoderCLIR"],"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":"/paper/classifying-scientific-publications-with-bert","slug":"classifying-scientific-publications-with-bert","title":"Classifying Scientific Publications with BERT -- Is Self-Attention a Feature Selection Method?","date":"2021-01-20","arxiv_id":"2101.08114","n_code_links":1,"syntology":null},{"paper":"/paper/divide-and-conquer-an-ensemble-approach-for","slug":"divide-and-conquer-an-ensemble-approach-for","title":"Divide and Conquer: An Ensemble Approach for Hostile Post Detection in Hindi","date":"2021-01-20","arxiv_id":"2101.07973","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-augment-for-data-scarce-domain","slug":"learning-to-augment-for-data-scarce-domain","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","date":"2021-01-20","arxiv_id":"2101.08106","n_code_links":0,"syntology":{"ran":2,"of":15,"n_ran_checked":2,"n_instrument":0,"unverified":13,"pointer_only":15,"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) · 13 unverified","official":null}},{"paper":"/paper/situation-and-behavior-understanding-by-trope","slug":"situation-and-behavior-understanding-by-trope","title":"Situation and Behavior Understanding by Trope Detection on Films","date":"2021-01-19","arxiv_id":"2101.07632","n_code_links":1,"syntology":null},{"paper":"/paper/towards-facilitating-empathic-conversations","slug":"towards-facilitating-empathic-conversations","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","date":"2021-01-19","arxiv_id":"2101.07714","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-punctuation-restoration-with-bert","slug":"automatic-punctuation-restoration-with-bert","title":"Automatic punctuation restoration with BERT models","date":"2021-01-18","arxiv_id":"2101.07343","n_code_links":1,"syntology":null},{"paper":"/paper/can-a-fruit-fly-learn-word-embeddings-1","slug":"can-a-fruit-fly-learn-word-embeddings-1","title":"Can a Fruit Fly Learn Word Embeddings?","date":"2021-01-18","arxiv_id":"2101.06887","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"transformer-based-models-for-question","title":"Transformer-Based Models for Question Answering on COVID19","date":"2021-01-16","arxiv_id":"2101.11432","n_code_links":0,"syntology":null},{"paper":null,"slug":"grid-search-hyperparameter-benchmarking-of","title":"Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC","date":"2021-01-15","arxiv_id":"2101.06326","n_code_links":0,"syntology":null},{"paper":null,"slug":"hostility-detection-and-covid-19-fake-news","title":"Hostility Detection and Covid-19 Fake News Detection in Social Media","date":"2021-01-15","arxiv_id":"2101.05953","n_code_links":0,"syntology":null},{"paper":null,"slug":"kdlsq-bert-a-quantized-bert-combining","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","date":"2021-01-15","arxiv_id":"2101.05938","n_code_links":0,"syntology":null},{"paper":"/paper/ecol-early-detection-of-covid-lies-using","slug":"ecol-early-detection-of-covid-lies-using","title":"ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information","date":"2021-01-14","arxiv_id":"2101.05499","n_code_links":1,"syntology":null},{"paper":"/paper/persistent-anti-muslim-bias-in-large-language","slug":"persistent-anti-muslim-bias-in-large-language","title":"Persistent Anti-Muslim Bias in Large Language Models","date":"2021-01-14","arxiv_id":"2101.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-language-model-fine-tuning","title":"Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection","date":"2021-01-14","arxiv_id":"2101.05509","n_code_links":0,"syntology":null},{"paper":null,"slug":"wer-bert-automatic-wer-estimation-with-bert","title":"WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm","date":"2021-01-14","arxiv_id":"2101.05478","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-deep-learning","title":"Experimental Evaluation of Deep Learning models for Marathi Text Classification","date":"2021-01-13","arxiv_id":"2101.04899","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-network-embedding-for-deep","title":"Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search","date":"2021-01-13","arxiv_id":"2101.04850","n_code_links":0,"syntology":null},{"paper":"/paper/ladiff-ulmfit-a-layer-differentiated-training","slug":"ladiff-ulmfit-a-layer-differentiated-training","title":"LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT","date":"2021-01-13","arxiv_id":"2101.04965","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-contract-element-extraction-revisited","title":"Neural Contract Element Extraction Revisited: Letters from Sesame Street","date":"2021-01-12","arxiv_id":"2101.04355","n_code_links":0,"syntology":null},{"paper":"/paper/of-non-linearity-and-commutativity-in-bert","slug":"of-non-linearity-and-commutativity-in-bert","title":"Of Non-Linearity and Commutativity in BERT","date":"2021-01-12","arxiv_id":"2101.04547","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-more-efficient-chinese-named-entity","title":"A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis","date":"2021-01-11","arxiv_id":"2101.11423","n_code_links":0,"syntology":null},{"paper":null,"slug":"at-bert-adversarial-training-bert-for-acronym","title":"AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21","date":"2021-01-11","arxiv_id":"2101.03700","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-deep-learning-models-for","title":"Evaluation of Deep Learning Models for Hostility Detection in Hindi Text","date":"2021-01-11","arxiv_id":"2101.04144","n_code_links":0,"syntology":null},{"paper":"/paper/bert-family-eat-word-salad-experiments-with","slug":"bert-family-eat-word-salad-experiments-with","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","date":"2021-01-10","arxiv_id":"2101.03453","n_code_links":1,"syntology":null},{"paper":"/paper/cisco-at-aaai-cad21-shared-task-predicting","slug":"cisco-at-aaai-cad21-shared-task-predicting","title":"Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings","date":"2021-01-10","arxiv_id":"2101.11422","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-sentence-representation-with","title":"Learning Better Sentence Representation with Syntax Information","date":"2021-01-09","arxiv_id":"2101.03343","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-non-local-alignment-over-full","slug":"contextual-non-local-alignment-over-full","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","date":"2021-01-08","arxiv_id":"2101.03036","n_code_links":2,"syntology":null},{"paper":null,"slug":"misspelling-correction-with-pre-trained","title":"Misspelling Correction with Pre-trained Contextual Language Model","date":"2021-01-08","arxiv_id":"2101.03204","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-transfer-learning-for-improving","title":"Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity","date":"2021-01-07","arxiv_id":"2101.02351","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-text-transformers-in-aaai-2021","slug":"exploring-text-transformers-in-aaai-2021","title":"Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English","date":"2021-01-07","arxiv_id":"2101.02359","n_code_links":1,"syntology":null},{"paper":null,"slug":"homonym-identification-using-bert-using-a","title":"Homonym Identification using BERT -- Using a Clustering Approach","date":"2021-01-07","arxiv_id":"2101.02398","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-comparative-analysis-of-methods-for","title":"COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data","date":"2021-01-05","arxiv_id":"2101.02017","n_code_links":0,"syntology":null},{"paper":"/paper/i-bert-integer-only-bert-quantization","slug":"i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","date":"2021-01-05","arxiv_id":"2101.01321","n_code_links":7,"syntology":null},{"paper":"/paper/improving-reference-mining-in-patents-with","slug":"improving-reference-mining-in-patents-with","title":"Improving reference mining in patents with BERT","date":"2021-01-04","arxiv_id":"2101.01039","n_code_links":1,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","n_code_links":1,"syntology":null},{"paper":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","n_code_links":2,"syntology":null},{"paper":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","n_code_links":2,"syntology":null},{"paper":"/paper/improving-sequence-to-sequence-pre-training","slug":"improving-sequence-to-sequence-pre-training","title":"Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting","date":"2021-01-02","arxiv_id":"2101.00416","n_code_links":1,"syntology":null},{"paper":null,"slug":"lex-bert-enhancing-bert-based-ner-with","title":"Lex-BERT: Enhancing BERT based NER with lexicons","date":"2021-01-02","arxiv_id":"2101.00396","n_code_links":0,"syntology":null},{"paper":"/paper/superbizarre-is-not-superb-improving-bert-s","slug":"superbizarre-is-not-superb-improving-bert-s","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","date":"2021-01-02","arxiv_id":"2101.00403","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["valentinhofmann/superbizarre"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-all-do-audio-transformer-models-hear","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","date":"2021-01-02","arxiv_id":"2101.00387","n_code_links":0,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-former-clustering-based-sparse-1","title":"Cluster-Former: Clustering-based Sparse Transformer for Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-tune-enhance-bert-performance-in-low","title":"Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-probe-bert-for-efficient-and-effective","title":"Cross-Probe BERT for Efficient and Effective Cross-Modal Search","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-increasing-the-efficiency-and","title":"DACT-BERT: Increasing the efficiency and interpretability of BERT by using adaptive computation time.","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-aware-low-rank-compression-for-large-nlp","title":"Data-aware Low-Rank Compression for Large NLP Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-proteins-using-a-triplet-bert","title":"Deep Learning Proteins using a Triplet-BERT network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-slot-relationship-modeling-using-a-pre","title":"Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"erasure-for-advancing-dynamic-self-supervised","title":"Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-vulnerabilities-of-bert-based-apis","title":"EXPLORING VULNERABILITIES OF BERT-BASED APIS","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-multipurpose-are-language-models","title":"How Multipurpose Are Language Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropy-in-the-contextual-embedding-space","title":"Isotropy in the Contextual Embedding Space: Clusters and Manifolds","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ketg-a-knowledge-enhanced-text-generation","title":"KETG: A Knowledge Enhanced Text Generation Framework","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modelling-drug-target-binding-affinity-using","title":"Modelling Drug-Target Binding Affinity using a BERT based Graph Neural network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-span-question-answering-using-span","title":"MULTI-SPAN QUESTION ANSWERING USING SPAN-IMAGE NETWORK","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-explaining-your-explanations-of-bert-an","slug":"on-explaining-your-explanations-of-bert-an","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","date":"2021-01-01","arxiv_id":"2101.00196","n_code_links":2,"syntology":null},{"paper":"/paper/polyjuice-automated-general-purpose","slug":"polyjuice-automated-general-purpose","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","date":"2021-01-01","arxiv_id":"2101.00288","n_code_links":1,"syntology":null},{"paper":null,"slug":"post-training-weighted-quantization-of-neural","title":"Post-Training Weighted Quantization of Neural Networks for Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-text-to-text-transformers-to","title":"Pre-training Text-to-Text Transformers to Write and Reason with Concepts","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","n_code_links":13,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiangLi1999/PrefixTuning"],"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":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify","title":"SkillBERT: “Skilling” the BERT to classify skills!","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speeding-up-deep-learning-training-by-sharing","title":"Speeding up Deep Learning Training by Sharing Weights and Then Unsharing","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-relevance-xlnet-word-embedding","title":"Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-notes-on-the-fly-helps-language-pre","title":"Taking Notes on the Fly Helps Language Pre-Training","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"task-agnostic-and-adaptive-size-bert","title":"Task-Agnostic and Adaptive-Size BERT Compression","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"c4306d3a26418a7692d3b23b9467be314a0aaf6287617e202656959e6f1900ae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}