{"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/191","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":191,"pages_in_order":250,"rows_per_page":100,"rows":[19001,19100],"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/190","next":"/method/layer-normalization/papers/192","papers":[{"paper":"/paper/ms-latte-a-dataset-of-where-and-when-to-do","slug":"ms-latte-a-dataset-of-where-and-when-to-do","title":"MS-LaTTE: A Dataset of Where and When To-do Tasks are Completed","date":"2021-11-12","arxiv_id":"2111.06902","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-channel-spatial-attention-based-vision","title":"The self-supervised spectral-spatial attention-based transformer network for automated, accurate prediction of crop nitrogen status from UAV imagery","date":"2021-11-12","arxiv_id":"2111.06839","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-image-compression","title":"Transformer-based Image Compression","date":"2021-11-12","arxiv_id":"2111.06707","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-visual-transformers","slug":"a-survey-of-visual-transformers","title":"A Survey of Visual Transformers","date":"2021-11-11","arxiv_id":"2111.06091","n_code_links":1,"syntology":null},{"paper":"/paper/automated-question-generation-and-question","slug":"automated-question-generation-and-question","title":"Automated question generation and question answering from Turkish texts","date":"2021-11-11","arxiv_id":"2111.06476","n_code_links":1,"syntology":null},{"paper":"/paper/character-level-hypernetworks-for-hate-speech","slug":"character-level-hypernetworks-for-hate-speech","title":"Character-level HyperNetworks for Hate Speech Detection","date":"2021-11-11","arxiv_id":"2111.06336","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-relation-transformer-incorporating","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","date":"2021-11-11","arxiv_id":"2111.06075","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-large-scale-language-models-and","title":"Improving Large-scale Language Models and Resources for Filipino","date":"2021-11-11","arxiv_id":"2111.06053","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-corpus-of-discourse-structure-in","slug":"a-novel-corpus-of-discourse-structure-in","title":"A Novel Corpus of Discourse Structure in Humans and Computers","date":"2021-11-10","arxiv_id":"2111.05940","n_code_links":1,"syntology":null},{"paper":null,"slug":"amazon-sagemaker-model-parallelism-a-general","title":"Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training","date":"2021-11-10","arxiv_id":"2111.05972","n_code_links":0,"syntology":null},{"paper":"/paper/attention-approximates-sparse-distributed","slug":"attention-approximates-sparse-distributed","title":"Attention Approximates Sparse Distributed Memory","date":"2021-11-10","arxiv_id":"2111.05498","n_code_links":1,"syntology":{"ran":12,"of":19,"n_ran_checked":11,"n_instrument":1,"unverified":7,"pointer_only":7,"phrase":"12 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; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["trentbrick/attention-approximates-sdm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/bagbert-bert-based-bagging-stacking-for-multi","slug":"bagbert-bert-based-bagging-stacking-for-multi","title":"BagBERT: BERT-based bagging-stacking for multi-topic classification","date":"2021-11-10","arxiv_id":"2111.05808","n_code_links":1,"syntology":null},{"paper":null,"slug":"cehr-bert-incorporating-temporal-information","title":"CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks","date":"2021-11-10","arxiv_id":"2111.08585","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-transformer-with-variable-length","slug":"multimodal-transformer-with-variable-length","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","date":"2021-11-10","arxiv_id":"2111.05759","n_code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","n_code_links":2,"syntology":null},{"paper":"/paper/soft-sensing-transformer-hundreds-of-sensors","slug":"soft-sensing-transformer-hundreds-of-sensors","title":"Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word","date":"2021-11-10","arxiv_id":"2111.05973","n_code_links":1,"syntology":null},{"paper":null,"slug":"distir-an-intermediate-representation-and","title":"DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution","date":"2021-11-09","arxiv_id":"2111.05426","n_code_links":0,"syntology":null},{"paper":null,"slug":"dsbert-unsupervised-dialogue-structure","title":"DSBERT:Unsupervised Dialogue Structure learning with BERT","date":"2021-11-09","arxiv_id":"2111.04933","n_code_links":0,"syntology":null},{"paper":null,"slug":"fpm-a-collection-of-large-scale-foundation","title":"FPM: A Collection of Large-scale Foundation Pre-trained Language Models","date":"2021-11-09","arxiv_id":"2111.04909","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-in-the-loop-disinformation-detection","title":"Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else?","date":"2021-11-09","arxiv_id":"2111.05139","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-prediction-of-clinical-outcomes-in","title":"Multi-Task Prediction of Clinical Outcomes in the Intensive Care Unit using Flexible Multimodal Transformers","date":"2021-11-09","arxiv_id":"2111.05431","n_code_links":0,"syntology":null},{"paper":"/paper/sliced-recursive-transformer-1","slug":"sliced-recursive-transformer-1","title":"Sliced Recursive Transformer","date":"2021-11-09","arxiv_id":"2111.05297","n_code_links":1,"syntology":null},{"paper":"/paper/ai-upv-at-iberlef-2021-detoxis-task-toxicity","slug":"ai-upv-at-iberlef-2021-detoxis-task-toxicity","title":"AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models","date":"2021-11-08","arxiv_id":"2111.04530","n_code_links":1,"syntology":null},{"paper":"/paper/chemical-detection-and-indexing-in-pubmed","slug":"chemical-detection-and-indexing-in-pubmed","title":"Chemical detection and indexing in PubMed full text articles using deep learning and rule-based methods","date":"2021-11-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-depression-in-thai-blog-posts-a-1","title":"Detecting Depression in Thai Blog Posts: a Dataset and a Baseline","date":"2021-11-08","arxiv_id":"2111.04574","n_code_links":0,"syntology":null},{"paper":"/paper/guiding-multi-step-rearrangement-tasks-with","slug":"guiding-multi-step-rearrangement-tasks-with","title":"Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions","date":"2021-11-08","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/mixed-transformer-u-net-for-medical-image","slug":"mixed-transformer-u-net-for-medical-image","title":"Mixed Transformer U-Net For Medical Image Segmentation","date":"2021-11-08","arxiv_id":"2111.04734","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 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) · 0 unverified","official":{"repos":["dootmaan/mt-unet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sexism-prediction-in-spanish-and-english","slug":"sexism-prediction-in-spanish-and-english","title":"Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models","date":"2021-11-08","arxiv_id":"2111.04551","n_code_links":1,"syntology":null},{"paper":"/paper/synthesizing-collective-communication","slug":"synthesizing-collective-communication","title":"TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches","date":"2021-11-08","arxiv_id":"2111.04867","n_code_links":2,"syntology":null},{"paper":"/paper/are-we-ready-for-a-new-paradigm-shift-a","slug":"are-we-ready-for-a-new-paradigm-shift-a","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","date":"2021-11-07","arxiv_id":"2111.04060","n_code_links":1,"syntology":null},{"paper":"/paper/tacl-improving-bert-pre-training-with-token","slug":"tacl-improving-bert-pre-training-with-token","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","date":"2021-11-07","arxiv_id":"2111.04198","n_code_links":2,"syntology":null},{"paper":null,"slug":"analyzing-architectures-for-neural-machine","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","date":"2021-11-06","arxiv_id":"2111.03813","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-data-driven-surrogate-simulators","slug":"benchmarking-data-driven-surrogate-simulators","title":"Benchmarking Data-driven Surrogate Simulators for Artificial Electromagnetic Materials","date":"2021-11-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-gated-mlp-combining","title":"Convolutional Gated MLP: Combining Convolutions & gMLP","date":"2021-11-06","arxiv_id":"2111.03940","n_code_links":0,"syntology":null},{"paper":null,"slug":"profitable-trade-off-between-memory-and","title":"Profitable Trade-Off Between Memory and Performance In Multi-Domain Chatbot Architectures","date":"2021-11-06","arxiv_id":"2111.03963","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-transformer-transducer-for","title":"Context-Aware Transformer Transducer for Speech Recognition","date":"2021-11-05","arxiv_id":"2111.03250","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-speech-recognition-leveraging","title":"Effective Cross-Utterance Language Modeling for Conversational Speech Recognition","date":"2021-11-05","arxiv_id":"2111.03333","n_code_links":0,"syntology":null},{"paper":null,"slug":"hepatic-vessel-segmentation-based-on-3dswin","title":"Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention","date":"2021-11-05","arxiv_id":"2111.03368","n_code_links":0,"syntology":null},{"paper":null,"slug":"ibert-idiom-cloze-style-reading-comprehension","title":"IBERT: Idiom Cloze-style reading comprehension with Attention","date":"2021-11-05","arxiv_id":"2112.02994","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-visual-quality-of-image-synthesis","title":"Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers","date":"2021-11-05","arxiv_id":"2111.03481","n_code_links":0,"syntology":null},{"paper":null,"slug":"oracle-teacher-towards-better-knowledge","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","date":"2021-11-05","arxiv_id":"2111.03664","n_code_links":0,"syntology":null},{"paper":null,"slug":"sexism-identification-in-tweets-and-gabs","title":"Sexism Identification in Tweets and Gabs using Deep Neural Networks","date":"2021-11-05","arxiv_id":"2111.03612","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-text-autoencoder-from-transformer-for-fast","title":"A text autoencoder from transformer for fast encoding language representation","date":"2021-11-04","arxiv_id":"2111.02844","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-the-effectiveness-of-an","slug":"an-empirical-study-of-the-effectiveness-of-an","title":"An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets","date":"2021-11-04","arxiv_id":"2111.03196","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-multimodal-automl-for-tabular","slug":"benchmarking-multimodal-automl-for-tabular","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","date":"2021-11-04","arxiv_id":"2111.02705","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sxjscience/automl_multimodal_benchmark","awslabs/autogluon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/conformal-prediction-for-text-infilling-and","slug":"conformal-prediction-for-text-infilling-and","title":"Conformal prediction for text infilling and part-of-speech prediction","date":"2021-11-04","arxiv_id":"2111.02592","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-radiograph-representation","slug":"generalized-radiograph-representation","title":"Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports","date":"2021-11-04","arxiv_id":"2111.03452","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["funnyzhou/refers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mt3-multi-task-multitrack-music-transcription-1","slug":"mt3-multi-task-multitrack-music-transcription-1","title":"MT3: Multi-Task Multitrack Music Transcription","date":"2021-11-04","arxiv_id":"2111.03017","n_code_links":3,"syntology":{"ran":0,"of":6,"n_ran_checked":0,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"0 ran · 6 unverified","official":{"repos":["magenta/mt3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"paper":null,"slug":"multi-airport-delay-prediction-with","title":"Multi-Airport Delay Prediction with Transformers","date":"2021-11-04","arxiv_id":"2111.04494","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-training-end-to-end","slug":"an-empirical-study-of-training-end-to-end","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","date":"2021-11-03","arxiv_id":"2111.02387","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zdou0830/meter"],"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/an-explanation-of-in-context-learning-as-1","slug":"an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","arxiv_id":"2111.02080","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/incontext-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-dre-bert-with-deep-recursive-encoder-for","title":"BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching","date":"2021-11-03","arxiv_id":"2111.02188","n_code_links":0,"syntology":null},{"paper":null,"slug":"prostformer-pre-trained-progressive-space","title":"ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting","date":"2021-11-03","arxiv_id":"2111.03459","n_code_links":0,"syntology":null},{"paper":null,"slug":"theeyecorpus-experiments-in-reducing-nlp-bias","title":"TheEyeCorpus: Experiments in Reducing NLP Bias and Identifiability for Large LMs","date":"2021-11-03","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transms-transformers-for-super-resolution","slug":"transms-transformers-for-super-resolution","title":"TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging","date":"2021-11-03","arxiv_id":"2111.02163","n_code_links":2,"syntology":null},{"paper":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-vision-transformers-perform-convolution-1","title":"Can Vision Transformers Perform Convolution?","date":"2021-11-02","arxiv_id":"2111.01353","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-hate-speech-using-bert-and-hate","title":"Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model","date":"2021-11-02","arxiv_id":"2111.01515","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-documents-relevance-to-search","title":"Explaining Documents' Relevance to Search Queries","date":"2021-11-02","arxiv_id":"2111.01314","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-vision-transformer-for-covid","title":"Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training","date":"2021-11-02","arxiv_id":"2111.01338","n_code_links":0,"syntology":null},{"paper":"/paper/relational-self-attention-what-s-missing-in","slug":"relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","arxiv_id":"2111.01673","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["KimManjin/RSA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sentence-encoding-for-dialogue-act","slug":"sentence-encoding-for-dialogue-act","title":"Sentence encoding for Dialogue Act classification","date":"2021-11-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/uquad1-0-development-of-an-urdu-question","slug":"uquad1-0-development-of-an-urdu-question","title":"UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension","date":"2021-11-02","arxiv_id":"2111.01543","n_code_links":0,"syntology":null},{"paper":null,"slug":"accounting-for-dependencies-in-deep-learning","title":"Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging","date":"2021-11-01","arxiv_id":"2111.01556","n_code_links":0,"syntology":null},{"paper":"/paper/arch-net-model-distillation-for-architecture","slug":"arch-net-model-distillation-for-architecture","title":"Arch-Net: Model Distillation for Architecture Agnostic Model Deployment","date":"2021-11-01","arxiv_id":"2111.01135","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-study-of-long-document","title":"Comparative Study of Long Document Classification","date":"2021-11-01","arxiv_id":"2111.00702","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-hate-speech-detection-using","title":"Cross-lingual Hate Speech Detection using Transformer Models","date":"2021-11-01","arxiv_id":"2111.00981","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-causal-associations-in-tweets","slug":"identifying-causal-associations-in-tweets","title":"Identifying causal relations in tweets using deep learning: Use case on diabetes-related tweets from 2017-2021","date":"2021-11-01","arxiv_id":"2111.01225","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-piano-music-with-sustain","slug":"learning-to-generate-piano-music-with-sustain","title":"Learning To Generate Piano Music With Sustain Pedals","date":"2021-11-01","arxiv_id":"2111.01216","n_code_links":1,"syntology":null},{"paper":"/paper/maple-masking-words-to-generate-blackout","slug":"maple-masking-words-to-generate-blackout","title":"MAPLE – MAsking words to generate blackout Poetry using sequence-to-sequence LEarning","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"recent-advances-in-natural-language","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","date":"2021-11-01","arxiv_id":"2111.01243","n_code_links":0,"syntology":null},{"paper":null,"slug":"vsec-transformer-based-model-for-vietnamese","title":"VSEC: Transformer-based Model for Vietnamese Spelling Correction","date":"2021-11-01","arxiv_id":"2111.00640","n_code_links":0,"syntology":null},{"paper":"/paper/wino-x-multilingual-winograd-schemas-for","slug":"wino-x-multilingual-winograd-schemas-for","title":"Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fineas-financial-embedding-analysis-of","slug":"fineas-financial-embedding-analysis-of","title":"FinEAS: Financial Embedding Analysis of Sentiment","date":"2021-10-31","arxiv_id":"2111.00526","n_code_links":1,"syntology":null},{"paper":"/paper/backdoor-pre-trained-models-can-transfer-to","slug":"backdoor-pre-trained-models-can-transfer-to","title":"Backdoor Pre-trained Models Can Transfer to All","date":"2021-10-30","arxiv_id":"2111.00197","n_code_links":1,"syntology":null},{"paper":"/paper/cross-modality-fusion-transformer-for","slug":"cross-modality-fusion-transformer-for","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","date":"2021-10-30","arxiv_id":"2111.00273","n_code_links":1,"syntology":null},{"paper":"/paper/dsee-dually-sparsity-embedded-efficient-1","slug":"dsee-dually-sparsity-embedded-efficient-1","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","date":"2021-10-30","arxiv_id":"2111.00160","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["vita-group/dsee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2021-10-30","arxiv_id":"2111.00230","n_code_links":0,"syntology":null},{"paper":"/paper/patchformer-a-versatile-3d-transformer-based","slug":"patchformer-a-versatile-3d-transformer-based","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","date":"2021-10-30","arxiv_id":"2111.00207","n_code_links":0,"syntology":null},{"paper":"/paper/amendable-generation-for-dialogue-state","slug":"amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","arxiv_id":"2110.15659","n_code_links":1,"syntology":null},{"paper":"/paper/delayed-propagation-transformer-a-universal","slug":"delayed-propagation-transformer-a-universal","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","date":"2021-10-29","arxiv_id":"2110.15926","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vita-group/dept"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rebel-relation-extraction-by-end-to-end","slug":"rebel-relation-extraction-by-end-to-end","title":"REBEL: Relation Extraction By End-to-end Language generation","date":"2021-10-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/structure-aware-fine-tuning-of-sequence-to","slug":"structure-aware-fine-tuning-of-sequence-to","title":"Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing","date":"2021-10-29","arxiv_id":"2110.15534","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-golden-rule-as-a-heuristic-to-measure-the","title":"The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning","date":"2021-10-29","arxiv_id":"2111.00107","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-sequence-tagging-framework-for","title":"ICDM 2020 Knowledge Graph Contest: Consumer Event-Cause Extraction","date":"2021-10-28","arxiv_id":"2110.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-model-for-extracting","title":"A Sequence to Sequence Model for Extracting Multiple Product Name Entities from Dialog","date":"2021-10-28","arxiv_id":"2110.14843","n_code_links":0,"syntology":null},{"paper":null,"slug":"blending-anti-aliasing-into-vision","title":"Blending Anti-Aliasing into Vision Transformer","date":"2021-10-28","arxiv_id":"2110.15156","n_code_links":0,"syntology":null},{"paper":"/paper/bridge-the-gap-between-cv-and-nlp-a-gradient","slug":"bridge-the-gap-between-cv-and-nlp-a-gradient","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2021-10-28","arxiv_id":"2110.15317","n_code_links":1,"syntology":null},{"paper":"/paper/colossal-ai-a-unified-deep-learning-system","slug":"colossal-ai-a-unified-deep-learning-system","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","date":"2021-10-28","arxiv_id":"2110.14883","n_code_links":1,"syntology":null},{"paper":null,"slug":"dispensed-transformer-network-for","title":"Dispensed Transformer Network for Unsupervised Domain Adaptation","date":"2021-10-28","arxiv_id":"2110.14944","n_code_links":0,"syntology":null},{"paper":null,"slug":"nxmtransformer-semi-structured-sparsification","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","date":"2021-10-28","arxiv_id":"2110.15766","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-attention-heads-of-transformer-models","title":"Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures","date":"2021-10-28","arxiv_id":"2110.15225","n_code_links":0,"syntology":null},{"paper":"/paper/scatterbrain-unifying-sparse-and-low-rank","slug":"scatterbrain-unifying-sparse-and-low-rank","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","date":"2021-10-28","arxiv_id":"2110.15343","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hazyresearch/scatterbrain"],"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/self-supervised-representation-learning-on-1","slug":"self-supervised-representation-learning-on-1","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","date":"2021-10-28","arxiv_id":"2110.15288","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"pointer_only":15,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hsg-aiml/neurips_2021-weight_space_learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/semi-siamese-bi-encoder-neural-ranking-model","slug":"semi-siamese-bi-encoder-neural-ranking-model","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","date":"2021-10-28","arxiv_id":"2110.14943","n_code_links":1,"syntology":null},{"paper":null,"slug":"anomaly-injected-deep-support-vector-data","title":"Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection","date":"2021-10-27","arxiv_id":"2110.14729","n_code_links":0,"syntology":null},{"paper":"/paper/ask-me-in-your-own-words-paraphrasing-for","slug":"ask-me-in-your-own-words-paraphrasing-for","title":"Ask me in your own words: paraphrasing for multitask question answering","date":"2021-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-dementia-from-speech-and","title":"Detecting Dementia from Speech and Transcripts using Transformers","date":"2021-10-27","arxiv_id":"2110.14769","n_code_links":0,"syntology":null},{"paper":"/paper/discovering-non-monotonic-autoregressive","slug":"discovering-non-monotonic-autoregressive","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","date":"2021-10-27","arxiv_id":"2110.15797","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":1,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["xuanlinli17/autoregressive_inference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-with-causal-counterfactual","title":"Transfer learning with causal counterfactual reasoning in Decision Transformers","date":"2021-10-27","arxiv_id":"2110.14355","n_code_links":0,"syntology":null}],"record_sha256":"ccbc92f4f932438ad9a695956cc77043e91711882b04150c59a8df558cffd33f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}