{"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/layer-normalization/papers/200","list_of":"/method/layer-normalization","method":"Layer Normalization","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":200,"pages_in_order":250,"rows_per_page":100,"rows":[19901,20000],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/199","next":"/method/layer-normalization/papers/201","papers":[{"paper":null,"slug":"abstractive-sentence-summarization-with-1","title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","date":"2021-08-11","arxiv_id":"2108.05123","n_code_links":0,"syntology":null},{"paper":null,"slug":"convnets-vs-transformers-whose-visual","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","date":"2021-08-11","arxiv_id":"2108.05305","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-vlbert-medical-visual-language-bert","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","date":"2021-08-11","arxiv_id":"2108.05067","n_code_links":0,"syntology":null},{"paper":null,"slug":"nofake-at-checkthat-2021-fake-news-detection","title":"NoFake at CheckThat! 2021: Fake News Detection Using BERT","date":"2021-08-11","arxiv_id":"2108.05419","n_code_links":0,"syntology":null},{"paper":"/paper/perturbing-inputs-for-fragile-interpretations","slug":"perturbing-inputs-for-fragile-interpretations","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","date":"2021-08-11","arxiv_id":"2108.04990","n_code_links":1,"syntology":null},{"paper":"/paper/variable-length-music-score-infilling-via","slug":"variable-length-music-score-infilling-via","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","date":"2021-08-11","arxiv_id":"2108.05064","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-social-and-behavioral-determinants","title":"A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models","date":"2021-08-10","arxiv_id":"2108.04949","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-multi-resolution-attention-with","title":"Adaptive Multi-Resolution Attention with Linear Complexity","date":"2021-08-10","arxiv_id":"2108.04962","n_code_links":0,"syntology":null},{"paper":"/paper/adarnn-adaptive-learning-and-forecasting-of","slug":"adarnn-adaptive-learning-and-forecasting-of","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","date":"2021-08-10","arxiv_id":"2108.04443","n_code_links":2,"syntology":null},{"paper":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","n_code_links":2,"syntology":{"ran":13,"of":13,"n_ran_checked":11,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"clsebert-contrastive-learning-for-syntax","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","date":"2021-08-10","arxiv_id":"2108.04556","n_code_links":0,"syntology":null},{"paper":"/paper/differentiable-subset-pruning-of-transformer","slug":"differentiable-subset-pruning-of-transformer","title":"Differentiable Subset Pruning of Transformer Heads","date":"2021-08-10","arxiv_id":"2108.04657","n_code_links":2,"syntology":null},{"paper":"/paper/embodied-bert-a-transformer-model-for","slug":"embodied-bert-a-transformer-model-for","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","date":"2021-08-10","arxiv_id":"2108.04927","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-user-behavior-retrieval-in-click","slug":"end-to-end-user-behavior-retrieval-in-click","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","date":"2021-08-10","arxiv_id":"2108.04468","n_code_links":1,"syntology":null},{"paper":null,"slug":"ft-tdr-frequency-guided-transformer-and-top","title":"FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting","date":"2021-08-10","arxiv_id":"2108.04424","n_code_links":0,"syntology":null},{"paper":"/paper/truman-trope-understanding-in-movies-and","slug":"truman-trope-understanding-in-movies-and","title":"TrUMAn: Trope Understanding in Movies and Animations","date":"2021-08-10","arxiv_id":"2108.04542","n_code_links":0,"syntology":null},{"paper":"/paper/do-images-really-do-the-talking-analysing-the","slug":"do-images-really-do-the-talking-analysing-the","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","date":"2021-08-09","arxiv_id":"2108.03886","n_code_links":1,"syntology":null},{"paper":"/paper/dossier-coliee-2021-leveraging-dense","slug":"dossier-coliee-2021-leveraging-dense","title":"DoSSIER@COLIEE 2021: Leveraging dense retrieval and summarization-based re-ranking for case law retrieval","date":"2021-08-09","arxiv_id":"2108.03937","n_code_links":1,"syntology":null},{"paper":"/paper/filming-multimodal-sarcasm-detection-with","slug":"filming-multimodal-sarcasm-detection-with","title":"FiLMing Multimodal Sarcasm Detection with Attention","date":"2021-08-09","arxiv_id":"2110.00416","n_code_links":1,"syntology":null},{"paper":null,"slug":"intent5-search-result-diversification-using","title":"IntenT5: Search Result Diversification using Causal Language Models","date":"2021-08-09","arxiv_id":"2108.04026","n_code_links":0,"syntology":null},{"paper":"/paper/making-transformers-solve-compositional-tasks","slug":"making-transformers-solve-compositional-tasks","title":"Making Transformers Solve Compositional Tasks","date":"2021-08-09","arxiv_id":"2108.04378","n_code_links":1,"syntology":null},{"paper":"/paper/paint-transformer-feed-forward-neural","slug":"paint-transformer-feed-forward-neural","title":"Paint Transformer: Feed Forward Neural Painting with Stroke Prediction","date":"2021-08-09","arxiv_id":"2108.03798","n_code_links":2,"syntology":null},{"paper":"/paper/raftmlp-do-mlp-based-models-dream-of-winning","slug":"raftmlp-do-mlp-based-models-dream-of-winning","title":"RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?","date":"2021-08-09","arxiv_id":"2108.04384","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-hw-tsc-s-offline-speech-translation","title":"The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation","date":"2021-08-09","arxiv_id":"2108.03845","n_code_links":0,"syntology":null},{"paper":"/paper/efficacy-of-bert-embeddings-on-predicting","slug":"efficacy-of-bert-embeddings-on-predicting","title":"Efficacy of BERT embeddings on predicting disaster from Twitter data","date":"2021-08-08","arxiv_id":"2108.10698","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-commonsense-knowledge-on","title":"Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims","date":"2021-08-08","arxiv_id":"2108.03731","n_code_links":0,"syntology":null},{"paper":"/paper/edge-augmented-graph-transformers-global-self","slug":"edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","arxiv_id":"2108.03348","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 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) · 1 unverified","official":{"repos":["shamim-hussain/egt","shamim-hussain/egt_pytorch","shamim-hussain/egt_triangular"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hetemotionnet-two-stream-heterogeneous-graph","slug":"hetemotionnet-two-stream-heterogeneous-graph","title":"HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition","date":"2021-08-07","arxiv_id":"2108.03354","n_code_links":2,"syntology":null},{"paper":"/paper/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","n_code_links":2,"syntology":null},{"paper":null,"slug":"vision-transformers-for-femur-fracture","title":"Vision Transformer for femur fracture classification","date":"2021-08-07","arxiv_id":"2108.03414","n_code_links":0,"syntology":null},{"paper":"/paper/deriving-disinformation-insights-from","slug":"deriving-disinformation-insights-from","title":"Deriving Disinformation Insights from Geolocalized Twitter Callouts","date":"2021-08-06","arxiv_id":"2108.03067","n_code_links":1,"syntology":null},{"paper":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","n_code_links":0,"syntology":null},{"paper":null,"slug":"rollout-event-triggered-control-reconciling","title":"Rollout event-triggered control: reconciling event- and time-triggered control","date":"2021-08-06","arxiv_id":"2108.02994","n_code_links":0,"syntology":null},{"paper":"/paper/simpler-is-better-few-shot-semantic","slug":"simpler-is-better-few-shot-semantic","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","date":"2021-08-06","arxiv_id":"2108.03032","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhiheLu/CWT-for-FSS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-right-to-talk-an-audio-visual-transformer","slug":"the-right-to-talk-an-audio-visual-transformer","title":"The Right to Talk: An Audio-Visual Transformer Approach","date":"2021-08-06","arxiv_id":"2108.03256","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-residue-wise-profile-fusion-for-low","title":"Adaptive Residue-wise Profile Fusion for Low Homologous Protein SecondaryStructure Prediction Using External Knowledge","date":"2021-08-05","arxiv_id":"2108.04176","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoupled-transformer-for-scalable-inference","title":"Decoupled Transformer for Scalable Inference in Open-domain Question Answering","date":"2021-08-05","arxiv_id":"2108.02765","n_code_links":0,"syntology":null},{"paper":null,"slug":"dp-gan-alleviating-mode-collapse-in-gan-via","title":"Alleviating Mode Collapse in GAN via Diversity Penalty Module","date":"2021-08-05","arxiv_id":"2108.02353","n_code_links":0,"syntology":null},{"paper":"/paper/fast-convergence-of-detr-with-spatially-1","slug":"fast-convergence-of-detr-with-spatially-1","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-08-05","arxiv_id":"2108.02404","n_code_links":1,"syntology":null},{"paper":"/paper/finetuning-pretrained-transformers-into","slug":"finetuning-pretrained-transformers-into","title":"Finetuning Pretrained Transformers into Variational Autoencoders","date":"2021-08-05","arxiv_id":"2108.02446","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-transfer-learning-with-pretrained","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","date":"2021-08-05","arxiv_id":"2108.02340","n_code_links":0,"syntology":null},{"paper":null,"slug":"rockgpt-reconstructing-three-dimensional","title":"RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation","date":"2021-08-05","arxiv_id":"2108.03132","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-on-the-news-to-improve","title":"Sentiment Analysis on the News to Improve Mental Health","date":"2021-08-05","arxiv_id":"2108.07706","n_code_links":0,"syntology":null},{"paper":"/paper/token-shift-transformer-for-video","slug":"token-shift-transformer-for-video","title":"Token Shift Transformer for Video Classification","date":"2021-08-05","arxiv_id":"2108.02432","n_code_links":3,"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":["VideoNetworks/TokShift-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":"transrefer3d-entity-and-relation-aware","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","date":"2021-08-05","arxiv_id":"2108.02388","n_code_links":0,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for-1","title":"WeChat Neural Machine Translation Systems for WMT21","date":"2021-08-05","arxiv_id":"2108.02401","n_code_links":0,"syntology":null},{"paper":"/paper/curriculum-learning-for-language-modeling","slug":"curriculum-learning-for-language-modeling","title":"Curriculum learning for language modeling","date":"2021-08-04","arxiv_id":"2108.02170","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spacemanidol/CurriculumLearningForLanguageModels"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"optimizing-latency-for-online-video","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","date":"2021-08-04","arxiv_id":"2108.02147","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-offset-block-embedding-array-robe-for","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","date":"2021-08-04","arxiv_id":"2108.02191","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dynamic-head-importance-computation","title":"A Dynamic Head Importance Computation Mechanism for Neural Machine Translation","date":"2021-08-03","arxiv_id":"2108.01377","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-multilingual-end-to-end-speech","slug":"a-study-of-multilingual-end-to-end-speech","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","date":"2021-08-03","arxiv_id":"2108.01280","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-feature-regularized-loss-for-weakly","title":"Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation","date":"2021-08-03","arxiv_id":"2108.01296","n_code_links":0,"syntology":null},{"paper":null,"slug":"exbert-an-external-knowledge-enhanced-bert","title":"ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference","date":"2021-08-03","arxiv_id":"2108.01589","n_code_links":0,"syntology":null},{"paper":null,"slug":"http2vec-embedding-of-http-requests-for","title":"HTTP2vec: Embedding of HTTP Requests for Detection of Anomalous Traffic","date":"2021-08-03","arxiv_id":"2108.01763","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-differentially-private-bert","title":"Large-Scale Differentially Private BERT","date":"2021-08-03","arxiv_id":"2108.01624","n_code_links":0,"syntology":null},{"paper":"/paper/q-pain-a-question-answering-dataset-to","slug":"q-pain-a-question-answering-dataset-to","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","date":"2021-08-03","arxiv_id":"2108.01764","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-with-progressive-sampling","slug":"vision-transformer-with-progressive-sampling","title":"Vision Transformer with Progressive Sampling","date":"2021-08-03","arxiv_id":"2108.01684","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yuexy/PS-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/changes-in-european-solidarity-before-and","slug":"changes-in-european-solidarity-before-and","title":"Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset","date":"2021-08-02","arxiv_id":"2108.01042","n_code_links":1,"syntology":null},{"paper":"/paper/congested-crowd-instance-localization-with","slug":"congested-crowd-instance-localization-with","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","date":"2021-08-02","arxiv_id":"2108.00584","n_code_links":1,"syntology":null},{"paper":"/paper/constrained-graphic-layout-generation-via","slug":"constrained-graphic-layout-generation-via","title":"Constrained Graphic Layout Generation via Latent Optimization","date":"2021-08-02","arxiv_id":"2108.00871","n_code_links":1,"syntology":null},{"paper":"/paper/lichee-improving-language-model-pre-training","slug":"lichee-improving-language-model-pre-training","title":"LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization","date":"2021-08-02","arxiv_id":"2108.00801","n_code_links":1,"syntology":null},{"paper":null,"slug":"musical-speech-a-transformer-based","title":"Musical Speech: A Transformer-based Composition Tool","date":"2021-08-02","arxiv_id":"2108.01043","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-aware-semi-autoregressive-semantic","title":"Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL","date":"2021-08-02","arxiv_id":"2108.00804","n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-neural-population","slug":"representation-learning-for-neural-population","title":"Representation learning for neural population activity with Neural Data Transformers","date":"2021-08-02","arxiv_id":"2108.01210","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["snel-repo/neural-data-transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/s-2-mlpv2-improved-spatial-shift-mlp","slug":"s-2-mlpv2-improved-spatial-shift-mlp","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","date":"2021-08-02","arxiv_id":"2108.01072","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":2,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"self-supervised-answer-retrieval-on-clinical","title":"Self-supervised Answer Retrieval on Clinical Notes","date":"2021-08-02","arxiv_id":"2108.00775","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-for-mining-feature-requests","slug":"transfer-learning-for-mining-feature-requests","title":"Transfer Learning for Mining Feature Requests and Bug Reports from Tweets and App Store Reviews","date":"2021-08-02","arxiv_id":"2108.00663","n_code_links":1,"syntology":null},{"paper":null,"slug":"1213li-at-semeval-2021-task-6-detection-of","title":"1213Li at SemEval-2021 Task 6: Detection of Propaganda with Multi-modal Attention and Pre-trained Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bidirectional-transformer-based-alignment","title":"A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adept-an-adjective-dependent-plausibility","title":"ADEPT: An Adjective-Dependent Plausibility Task","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/are-pretrained-convolutions-better-than","slug":"are-pretrained-convolutions-better-than","title":"Are Pretrained Convolutions Better than Pretrained Transformers?","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"astartwice-at-semeval-2021-task-5-toxic-span","title":"AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attestable-at-semeval-2021-task-9-extending","slug":"attestable-at-semeval-2021-task-9-extending","title":"AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bennettnlp-at-semeval-2021-task-5-toxic-spans","title":"BennettNLP at SemEval-2021 Task 5: Toxic Spans Detection using Stacked Embedding Powered Toxic Entity Recognizer","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bertac-enhancing-transformer-based-language","slug":"bertac-enhancing-transformer-based-language","title":"BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-making-high-accuracy-non","title":"Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/beyond-sentence-level-end-to-end-speech","slug":"beyond-sentence-level-end-to-end-speech","title":"Beyond Sentence-Level End-to-End Speech Translation: Context Helps","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"can-transformer-models-measure-coherence-in","title":"Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cmta-covid-19-misinformation-multilingual","title":"CMTA: COVID-19 Misinformation Multilingual Analysis on Twitter","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-evidence-improves-monolingual","slug":"cross-lingual-evidence-improves-monolingual","title":"Cross-lingual Evidence Improves Monolingual Fake News Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-1-fusion-of","title":"CSECU-DSG at SemEval-2021 Task 1: Fusion of Transformer Models for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-5-leveraging","title":"CSECU-DSG at SemEval-2021 Task 5: Leveraging Ensemble of Sequence Tagging Models for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-6","title":"CSECU-DSG at SemEval-2021 Task 6: Orchestrating Multimodal Neural Architectures for Identifying Persuasion Techniques in Texts and Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-7-detecting","title":"CSECU-DSG at SemEval-2021 Task 7: Detecting and Rating Humor and Offense Employing Transformers","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ctfn-hierarchical-learning-for-multimodal","slug":"ctfn-hierarchical-learning-for-multimodal","title":"CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-differential-amplifier-for-extractive","title":"Deep Differential Amplifier for Extractive Summarization","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deepblueai-at-semeval-2021-task-7-detecting","title":"DeepBlueAI at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Stacking Diverse Language Model-Based Methods","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dljust-at-semeval-2021-task-7-hahackathon","title":"DLJUST at SemEval-2021 Task 7: Hahackathon: Linking Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/early-detection-of-sexual-predators-in-chats","slug":"early-detection-of-sexual-predators-in-chats","title":"Early Detection of Sexual Predators in Chats","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ecco-an-open-source-library-for-the","slug":"ecco-an-open-source-library-for-the","title":"Ecco: An Open Source Library for the Explainability of Transformer Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emlm-a-new-pre-training-objective-for-emotion","slug":"emlm-a-new-pre-training-objective-for-emotion","title":"eMLM: A New Pre-training Objective for Emotion Related Tasks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/employing-argumentation-knowledge-graphs-for","slug":"employing-argumentation-knowledge-graphs-for","title":"Employing Argumentation Knowledge Graphs for Neural Argument Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"endtimes-at-semeval-2021-task-7-detecting-and","title":"EndTimes at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with BERT and Ensembles","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-content-preservation-in-text-style","slug":"enhancing-content-preservation-in-text-style","title":"Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization","date":"2021-08-01","arxiv_id":"2108.00449","n_code_links":1,"syntology":null},{"paper":null,"slug":"es-just-at-semeval-2021-task-7-detecting-and","title":"ES-JUST at SemEval-2021 Task 7: Detecting and Rating Humor and Offensive Text Using Deep Learning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-contextualization-in-language","title":"Explaining Contextualization in Language Models using Visual Analytics","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explanations-for-commonsenseqa-new-dataset","slug":"explanations-for-commonsenseqa-new-dataset","title":"Explanations for CommonsenseQA: New Dataset and Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-listwise-evidence-reasoning-with-t5","title":"Exploring Listwise Evidence Reasoning with T5 for Fact Verification","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-neural-machine-translation","title":"Fast and Accurate Neural Machine Translation with Translation Memory","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ghost-at-semeval-2021-task-5-is-explanation","title":"GHOST at SemEval-2021 Task 5: Is explanation all you need?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"393a71c3bdcd4f12cf40633d1a6074dce5448defa68377ad1a310e135fcac72c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}