{"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/papers/281","list_of":"/method/attention","method":"Attention","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":281,"pages_in_order":316,"rows_per_page":100,"rows":[28001,28100],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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","prev":"/method/attention/papers/280","next":"/method/attention/papers/282","papers":[{"paper":null,"slug":"multi-task-time-series-forecasting-with","title":"Multi-Task Time Series Forecasting With Shared Attention","date":"2021-01-24","arxiv_id":"2101.09645","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/towards-a-better-integration-of-fuzzy-matches","slug":"towards-a-better-integration-of-fuzzy-matches","title":"Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data Augmentation","date":"2021-01-24","arxiv_id":null,"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":"enriching-non-autoregressive-transformer-with","title":"Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation","date":"2021-01-22","arxiv_id":"2101.08942","n_code_links":0,"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":null,"slug":"visual-question-answering-based-on-local","title":"Visual Question Answering based on Local-Scene-Aware Referring Expression Generation","date":"2021-01-22","arxiv_id":"2101.08978","n_code_links":0,"syntology":null},{"paper":"/paper/activity-graph-transformer-for-temporal","slug":"activity-graph-transformer-for-temporal","title":"Activity Graph Transformer for Temporal Action Localization","date":"2021-01-21","arxiv_id":"2101.08540","n_code_links":0,"syntology":null},{"paper":"/paper/daf-re-a-challenging-crowd-sourced-large","slug":"daf-re-a-challenging-crowd-sourced-large","title":"DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition","date":"2021-01-21","arxiv_id":"2101.08674","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":["arkel23/animesion"],"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/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/learn-to-dance-with-aist-music-conditioned-3d","slug":"learn-to-dance-with-aist-music-conditioned-3d","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","date":"2021-01-21","arxiv_id":"2101.08779","n_code_links":1,"syntology":null},{"paper":null,"slug":"active-learning-for-sequence-tagging-with","title":"Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates","date":"2021-01-20","arxiv_id":"2101.08133","n_code_links":0,"syntology":null},{"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/open-domain-conversational-search-assistant","slug":"open-domain-conversational-search-assistant","title":"Open-Domain Conversational Search Assistant with Transformers","date":"2021-01-20","arxiv_id":"2101.08197","n_code_links":1,"syntology":null},{"paper":"/paper/pgt-pseudo-relevance-feedback-using-a-graph","slug":"pgt-pseudo-relevance-feedback-using-a-graph","title":"PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer","date":"2021-01-20","arxiv_id":"2101.07918","n_code_links":1,"syntology":null},{"paper":"/paper/updet-universal-multi-agent-reinforcement","slug":"updet-universal-multi-agent-reinforcement","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","date":"2021-01-20","arxiv_id":"2101.08001","n_code_links":1,"syntology":null},{"paper":"/paper/fast-convergence-of-detr-with-spatially","slug":"fast-convergence-of-detr-with-spatially","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-01-19","arxiv_id":"2101.07448","n_code_links":2,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["gaopengcuhk/SMCA-DETR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/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":"/paper/inference-for-bart-with-multinomial-outcomes","slug":"inference-for-bart-with-multinomial-outcomes","title":"Inference for BART with Multinomial Outcomes","date":"2021-01-18","arxiv_id":"2101.06823","n_code_links":1,"syntology":null},{"paper":"/paper/dual-level-collaborative-transformer-for","slug":"dual-level-collaborative-transformer-for","title":"Dual-Level Collaborative Transformer for Image Captioning","date":"2021-01-16","arxiv_id":"2101.06462","n_code_links":1,"syntology":null},{"paper":"/paper/match-ignition-plugging-pagerank-into","slug":"match-ignition-plugging-pagerank-into","title":"Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching","date":"2021-01-16","arxiv_id":"2101.06423","n_code_links":1,"syntology":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":null,"slug":"exploration-of-visual-features-and-their","title":"Exploration of Visual Features and their weighted-additive fusion for Video Captioning","date":"2021-01-14","arxiv_id":"2101.05806","n_code_links":0,"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":"privacy-analysis-in-language-models-via","title":"Training Data Leakage Analysis in Language Models","date":"2021-01-14","arxiv_id":"2101.05405","n_code_links":0,"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":"/paper/coarse-and-fine-grained-hostility-detection","slug":"coarse-and-fine-grained-hostility-detection","title":"Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings","date":"2021-01-13","arxiv_id":"2101.04998","n_code_links":1,"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":"fake-news-detection-system-using-xlnet-model","title":"Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task","date":"2021-01-12","arxiv_id":"2101.11425","n_code_links":0,"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":null,"slug":"neural-news-recommendation-with-negative","title":"Neural News Recommendation with Negative Feedback","date":"2021-01-12","arxiv_id":"2101.04328","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":"/paper/bert-gt-cross-sentence-n-ary-relation","slug":"bert-gt-cross-sentence-n-ary-relation","title":"BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer","date":"2021-01-11","arxiv_id":"2101.04158","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":null,"slug":"investigating-the-vision-transformer-model","title":"Investigating the Vision Transformer Model for Image Retrieval Tasks","date":"2021-01-11","arxiv_id":"2101.03771","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-mahalanobis-distance-for","slug":"revisiting-mahalanobis-distance-for","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","date":"2021-01-11","arxiv_id":"2101.03778","n_code_links":1,"syntology":null},{"paper":null,"slug":"spherical-transformer-adapting-spherical","title":"Spherical Transformer: Adapting Spherical Signal to CNNs","date":"2021-01-11","arxiv_id":"2101.03848","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-slodderwetenschap-sloppy-science-of","title":"The Slodderwetenschap (Sloppy Science) of Stochastic Parrots -- A Plea for Science to NOT take the Route Advocated by Gebru and Bender","date":"2021-01-11","arxiv_id":"2101.10098","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":null,"slug":"channel-boosting-feature-ensemble-for-radar","title":"Channel Boosting Feature Ensemble for Radar-based Object Detection","date":"2021-01-10","arxiv_id":"2101.03531","n_code_links":0,"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":"/paper/deep-reinforcement-learning-with-function","slug":"deep-reinforcement-learning-with-function","title":"Deep Reinforcement Learning with Function Properties in Mean Reversion Strategies","date":"2021-01-09","arxiv_id":"2101.03418","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/trankit-a-light-weight-transformer-based","slug":"trankit-a-light-weight-transformer-based","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","date":"2021-01-09","arxiv_id":"2101.03289","n_code_links":1,"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":"/paper/leveraging-multilingual-transformers-for-hate","slug":"leveraging-multilingual-transformers-for-hate","title":"Leveraging Multilingual Transformers for Hate Speech Detection","date":"2021-01-08","arxiv_id":"2101.03207","n_code_links":1,"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/compound-word-transformer-learning-to-compose","slug":"compound-word-transformer-learning-to-compose","title":"Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs","date":"2021-01-07","arxiv_id":"2101.02402","n_code_links":5,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["YatingMusic/compound-word-transformer"],"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":"detecting-log-anomalies-with-multi-head","title":"Detecting Log Anomalies with Multi-Head Attention (LAMA)","date":"2021-01-07","arxiv_id":"2101.02392","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":"/paper/trackformer-multi-object-tracking-with","slug":"trackformer-multi-object-tracking-with","title":"TrackFormer: Multi-Object Tracking with Transformers","date":"2021-01-07","arxiv_id":"2101.02702","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-based-approach-towards-music","slug":"transformer-based-approach-towards-music","title":"Transformer-based approach towards music emotion recognition from lyrics","date":"2021-01-06","arxiv_id":"2101.02051","n_code_links":1,"syntology":null},{"paper":"/paper/autodropout-learning-dropout-patterns-to","slug":"autodropout-learning-dropout-patterns-to","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","date":"2021-01-05","arxiv_id":"2101.01761","n_code_links":1,"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/transformers-and-transfer-learning-for","slug":"transformers-and-transfer-learning-for","title":"Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning","date":"2021-01-04","arxiv_id":"2101.01213","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-in-vision-a-survey","title":"Transformers in Vision: A Survey","date":"2021-01-04","arxiv_id":"2101.01169","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-bart-for-multiobjective-optimization-of","title":"Using BART to Perform Pareto Optimization and Quantify its Uncertainties","date":"2021-01-04","arxiv_id":"2101.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-transformer-decoder-with","title":"An Efficient Transformer Decoder with Compressed Sub-layers","date":"2021-01-03","arxiv_id":"2101.00542","n_code_links":0,"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":"/paper/km-bart-knowledge-enhanced-multimodal-bart","slug":"km-bart-knowledge-enhanced-multimodal-bart","title":"KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation","date":"2021-01-02","arxiv_id":"2101.00419","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":"/paper/zero-shot-learning-by-generating-task","slug":"zero-shot-learning-by-generating-task","title":"Learning to Generate Task-Specific Adapters from Task Description","date":"2021-01-02","arxiv_id":"2101.00420","n_code_links":1,"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":"analogical-reasoning-for-visually-grounded-1","title":"Analogical Reasoning for Visually Grounded Compositional Generalization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ariel-volume-coding-for-sentence-generation-1","title":"AriEL: Volume Coding for Sentence Generation Comparisons","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-not-enough-mitigating-the","title":"Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"block-skim-transformer-for-efficient-question","title":"Block Skim Transformer for Efficient Question Answering","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":"causal-probabilistic-spatio-temporal-fusion","title":"Causal Probabilistic Spatio-temporal Fusion Transformers in Two-sided Ride-Hailing Markets","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}],"record_sha256":"3eafd21d609d98fef171e000ccce7b39c206ada91df5ef5df1c97901bd174e6f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}