{"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/196","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":196,"pages_in_order":250,"rows_per_page":100,"rows":[19501,19600],"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/195","next":"/method/layer-normalization/papers/197","papers":[{"paper":null,"slug":"dense-contrastive-visual-linguistic","title":"Dense Contrastive Visual-Linguistic Pretraining","date":"2021-09-24","arxiv_id":"2109.11778","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-enzymatic-active-sites-with","title":"Identification of Enzymatic Active Sites with Unsupervised Language Modeling","date":"2021-09-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lacking-the-embedding-of-a-word-look-it-up","title":"Lacking the embedding of a word? Look it up into a traditional dictionary","date":"2021-09-24","arxiv_id":"2109.11763","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-pretrained-models-for-automatic","slug":"leveraging-pretrained-models-for-automatic","title":"Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations","date":"2021-09-24","arxiv_id":"2109.12174","n_code_links":1,"syntology":null},{"paper":null,"slug":"localizing-infinity-shaped-fishes-sketch","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","date":"2021-09-24","arxiv_id":"2109.11874","n_code_links":0,"syntology":null},{"paper":"/paper/long-range-transformers-for-dynamic","slug":"long-range-transformers-for-dynamic","title":"Long-Range Transformers for Dynamic Spatiotemporal Forecasting","date":"2021-09-24","arxiv_id":"2109.12218","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["qdata/spacetimeformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robustness-and-sensitivity-of-bert-models","title":"Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text","date":"2021-09-24","arxiv_id":"2109.11888","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-generalize-linearly","slug":"transformers-generalize-linearly","title":"Transformers Generalize Linearly","date":"2021-09-24","arxiv_id":"2109.12036","n_code_links":1,"syntology":null},{"paper":"/paper/breaking-bert-understanding-its","slug":"breaking-bert-understanding-its","title":"Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack","date":"2021-09-23","arxiv_id":"2109.11308","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-linguistic-knowledge-for","title":"Dependency Structure for News Document Summarization","date":"2021-09-23","arxiv_id":"2109.11199","n_code_links":0,"syntology":null},{"paper":null,"slug":"oh-former-omni-relational-high-order","title":"OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification","date":"2021-09-23","arxiv_id":"2109.11159","n_code_links":0,"syntology":null},{"paper":"/paper/putting-words-in-bert-s-mouth-navigating","slug":"putting-words-in-bert-s-mouth-navigating","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","date":"2021-09-23","arxiv_id":"2109.11491","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-volctrans-glat-system-non-autoregressive","title":"The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21","date":"2021-09-23","arxiv_id":"2109.11247","n_code_links":0,"syntology":null},{"paper":null,"slug":"alzheimers-dementia-detection-using-acoustic","title":"Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT","date":"2021-09-22","arxiv_id":"2109.11010","n_code_links":0,"syntology":null},{"paper":"/paper/controlled-evaluation-of-grammatical","slug":"controlled-evaluation-of-grammatical","title":"Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models","date":"2021-09-22","arxiv_id":"2109.11058","n_code_links":1,"syntology":null},{"paper":null,"slug":"dialoguebert-a-self-supervised-learning-based","title":"DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder","date":"2021-09-22","arxiv_id":"2109.10480","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-multimodal-transformer-to","slug":"hierarchical-multimodal-transformer-to","title":"Hierarchical Multimodal Transformer to Summarize Videos","date":"2021-09-22","arxiv_id":"2109.10559","n_code_links":0,"syntology":null},{"paper":"/paper/improving-360-monocular-depth-estimation-via","slug":"improving-360-monocular-depth-estimation-via","title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","date":"2021-09-22","arxiv_id":"2109.10563","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":"/paper/kd-vlp-improving-end-to-end-vision-and","slug":"kd-vlp-improving-end-to-end-vision-and","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","date":"2021-09-22","arxiv_id":"2109.10504","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-models-as-recommender-systems","title":"Language Models as Recommender Systems: Evaluations and Limitations","date":"2021-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-efficiency-effectiveness-trade","title":"Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection","date":"2021-09-22","arxiv_id":"2109.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"recursively-summarizing-books-with-human","title":"Recursively Summarizing Books with Human Feedback","date":"2021-09-22","arxiv_id":"2109.10862","n_code_links":0,"syntology":null},{"paper":"/paper/scale-efficiently-insights-from-pre-training","slug":"scale-efficiently-insights-from-pre-training","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","date":"2021-09-22","arxiv_id":"2109.10686","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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":"t6d-direct-transformers-for-multi-object-6d","title":"T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression","date":"2021-09-22","arxiv_id":"2109.10948","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-niutrans-machine-translation-systems-for-1","title":"The NiuTrans Machine Translation Systems for WMT21","date":"2021-09-22","arxiv_id":"2109.10485","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-contextualized-document","slug":"unsupervised-contextualized-document","title":"Unsupervised Contextualized Document Representation","date":"2021-09-22","arxiv_id":"2109.10509","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-review-on-summarizing","title":"A Comprehensive Review on Summarizing Financial News Using Deep Learning","date":"2021-09-21","arxiv_id":"2109.10118","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertweetfr-domain-adaptation-of-pre-trained","title":"BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets","date":"2021-09-21","arxiv_id":"2109.10234","n_code_links":0,"syntology":null},{"paper":"/paper/ds-net-dynamic-weight-slicing-for-efficient","slug":"ds-net-dynamic-weight-slicing-for-efficient","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","date":"2021-09-21","arxiv_id":"2109.10060","n_code_links":1,"syntology":null},{"paper":null,"slug":"invbert-text-reconstruction-from","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","date":"2021-09-21","arxiv_id":"2109.10104","n_code_links":0,"syntology":null},{"paper":"/paper/lotr-face-landmark-localization-using","slug":"lotr-face-landmark-localization-using","title":"LOTR: Face Landmark Localization Using Localization Transformer","date":"2021-09-21","arxiv_id":"2109.10057","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-sentiment-emotion","title":"Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language","date":"2021-09-21","arxiv_id":"2109.10255","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-short-text","title":"Representation Learning for Short Text Clustering","date":"2021-09-21","arxiv_id":"2109.09894","n_code_links":0,"syntology":null},{"paper":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","n_code_links":8,"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, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/unilm"],"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/a-plug-and-play-method-for-controlled-text","slug":"a-plug-and-play-method-for-controlled-text","title":"A Plug-and-Play Method for Controlled Text Generation","date":"2021-09-20","arxiv_id":"2109.09707","n_code_links":1,"syntology":null},{"paper":"/paper/bartpho-pre-trained-sequence-to-sequence","slug":"bartpho-pre-trained-sequence-to-sequence","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","date":"2021-09-20","arxiv_id":"2109.09701","n_code_links":3,"syntology":null},{"paper":null,"slug":"bert-cannot-align-characters","title":"BERT Cannot Align Characters","date":"2021-09-20","arxiv_id":"2109.09700","n_code_links":0,"syntology":null},{"paper":"/paper/bert-has-uncommon-sense-similarity-ranking","slug":"bert-has-uncommon-sense-similarity-ranking","title":"BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology","date":"2021-09-20","arxiv_id":"2109.09780","n_code_links":1,"syntology":null},{"paper":null,"slug":"dyadformer-a-multi-modal-transformer-for-long","title":"Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions","date":"2021-09-20","arxiv_id":"2109.09487","n_code_links":0,"syntology":null},{"paper":null,"slug":"irnn-integer-only-recurrent-neural-network","title":"iRNN: Integer-only Recurrent Neural Network","date":"2021-09-20","arxiv_id":"2109.09828","n_code_links":0,"syntology":null},{"paper":null,"slug":"mfevit-a-robust-lightweight-transformer-based","title":"MFEViT: A Robust Lightweight Transformer-based Network for Multimodal 2D+3D Facial Expression Recognition","date":"2021-09-20","arxiv_id":"2109.13086","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-bias-in-nlp-application-to-hate-speech","title":"Model Bias in NLP -- Application to Hate Speech Classification using transfer learning techniques","date":"2021-09-20","arxiv_id":"2109.09725","n_code_links":0,"syntology":null},{"paper":"/paper/well-googled-is-half-done-multimodal","slug":"well-googled-is-half-done-multimodal","title":"Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends","date":"2021-09-20","arxiv_id":"2109.09824","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["humaticslab/gtm-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cliff-contrastive-learning-for-improving","slug":"cliff-contrastive-learning-for-improving","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","date":"2021-09-19","arxiv_id":"2109.09209","n_code_links":3,"syntology":null},{"paper":null,"slug":"do-long-range-language-models-actually-use","title":"Do Long-Range Language Models Actually Use Long-Range Context?","date":"2021-09-19","arxiv_id":"2109.09115","n_code_links":0,"syntology":null},{"paper":"/paper/mirrorwic-on-eliciting-word-in-context","slug":"mirrorwic-on-eliciting-word-in-context","title":"MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models","date":"2021-09-19","arxiv_id":"2109.09237","n_code_links":1,"syntology":null},{"paper":"/paper/the-seismo-performer-a-novel-machine-learning","slug":"the-seismo-performer-a-novel-machine-learning","title":"The Seismo-Performer: A Novel Machine Learning Approach for General and Efficient Seismic Phase Recognition from Local Earthquakes in Real Time","date":"2021-09-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-zero-label-language-learning","title":"Towards Zero-Label Language Learning","date":"2021-09-19","arxiv_id":"2109.09193","n_code_links":0,"syntology":null},{"paper":null,"slug":"wav-bert-cooperative-acoustic-and-linguistic","title":"Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition","date":"2021-09-19","arxiv_id":"2109.09161","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-bert-based-language-models-learn-in","title":"What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study","date":"2021-09-19","arxiv_id":"2109.09105","n_code_links":0,"syntology":null},{"paper":"/paper/complex-temporal-question-answering-on","slug":"complex-temporal-question-answering-on","title":"Complex Temporal Question Answering on Knowledge Graphs","date":"2021-09-18","arxiv_id":"2109.08935","n_code_links":1,"syntology":null},{"paper":"/paper/dylex-incoporating-dynamic-lexicons-into-bert","slug":"dylex-incoporating-dynamic-lexicons-into-bert","title":"DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling","date":"2021-09-18","arxiv_id":"2109.08818","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-hybrid-transformer-learning-global","slug":"efficient-hybrid-transformer-learning-global","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","date":"2021-09-18","arxiv_id":"2109.08937","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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["WangLibo1995/GeoSeg"],"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":null,"slug":"sdtp-semantic-aware-decoupled-transformer","title":"SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction","date":"2021-09-18","arxiv_id":"2109.08963","n_code_links":0,"syntology":null},{"paper":"/paper/text-detoxification-using-large-pre-trained","slug":"text-detoxification-using-large-pre-trained","title":"Text Detoxification using Large Pre-trained Neural Models","date":"2021-09-18","arxiv_id":"2109.08914","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skoltech-nlp/detox"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-high-quality-temporal-action","slug":"towards-high-quality-temporal-action","title":"Towards High-Quality Temporal Action Detection with Sparse Proposals","date":"2021-09-18","arxiv_id":"2109.08847","n_code_links":1,"syntology":null},{"paper":null,"slug":"commonsense-knowledge-augmented-pretrained","title":"Commonsense Knowledge-Augmented Pretrained Language Models for Causal Reasoning Classification","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-vs-target-word-quantifying-biases","title":"Context vs Target Word: Quantifying Biases When Applying Models to Lexical Semantic Datasets","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-streaming-multi-talker-asr-with","title":"Continuous Streaming Multi-Talker ASR with Dual-path Transducers","date":"2021-09-17","arxiv_id":"2109.08555","n_code_links":0,"syntology":null},{"paper":null,"slug":"defending-textual-neural-networks-against","title":"Defending Textual Neural Networks against Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"digging-errors-in-nmt-evaluating-and","title":"Digging Errors in NMT: Evaluating and Understanding Model Errors from Hypothesis Distribution","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"does-bert-really-agree-fine-grained-analysis","title":"Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"expression-snippet-transformer-for-robust","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","date":"2021-09-17","arxiv_id":"2109.08409","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuned-transformers-show-clusters-of","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","date":"2021-09-17","arxiv_id":"2109.08406","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-known-to-unknown-knowledge-guided","title":"From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba","date":"2021-09-17","arxiv_id":"2109.08381","n_code_links":0,"syntology":null},{"paper":"/paper/grounding-natural-language-instructions-can","slug":"grounding-natural-language-instructions-can","title":"Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?","date":"2021-09-17","arxiv_id":"2109.08634","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchy-aware-t5-with-path-adaptive-mask","title":"Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification","date":"2021-09-17","arxiv_id":"2109.08585","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-neurons-in-pretrained-transformers-1","title":"Knowledge Neurons in Pretrained Transformers","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-low-frequency-patterns-with-a-pre","title":"Learning Low-frequency Patterns with A Pre-trained Document-Grounded Conversation Model","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/new-students-on-sesame-street-what-order","slug":"new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","n_code_links":1,"syntology":null},{"paper":"/paper/primer-searching-for-efficient-transformers","slug":"primer-searching-for-efficient-transformers","title":"Primer: Searching for Efficient Transformers for Language Modeling","date":"2021-09-17","arxiv_id":"2109.08668","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"relating-neural-text-degeneration-to-exposure","title":"Relating Neural Text Degeneration to Exposure Bias","date":"2021-09-17","arxiv_id":"2109.08705","n_code_links":0,"syntology":null},{"paper":null,"slug":"remixers-a-mixer-transformer-architecture","title":"Remixers: A Mixer-Transformer Architecture with Compositional Operators for Natural Language Understanding","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-vs-model-architectures-how-does","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? An Extensive Empirical Study on Language Tasks","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-futility-of-stilts-for-the-classification","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","date":"2021-09-17","arxiv_id":"2109.08607","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-jhu-microsoft-submission-for-wmt21","title":"The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task","date":"2021-09-17","arxiv_id":"2109.08724","n_code_links":0,"syntology":null},{"paper":"/paper/an-end-to-end-transformer-model-for-3d-object","slug":"an-end-to-end-transformer-model-for-3d-object","title":"An End-to-End Transformer Model for 3D Object Detection","date":"2021-09-16","arxiv_id":"2109.08141","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/fast-slow-transformer-for-visually-grounding","slug":"fast-slow-transformer-for-visually-grounding","title":"Fast-Slow Transformer for Visually Grounding Speech","date":"2021-09-16","arxiv_id":"2109.08186","n_code_links":1,"syntology":null},{"paper":"/paper/generative-pre-training-from-molecules","slug":"generative-pre-training-from-molecules","title":"Generative Pre-Training from Molecules","date":"2021-09-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/label-attention-transformer-with","slug":"label-attention-transformer-with","title":"Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning","date":"2021-09-16","arxiv_id":"2109.07799","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-are-few-shot-multilingual","slug":"language-models-are-few-shot-multilingual","title":"Language Models are Few-shot Multilingual Learners","date":"2021-09-16","arxiv_id":"2109.07684","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gentaiscool/few-shot-lm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"let-the-cat-out-of-the-bag-contrastive","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","date":"2021-09-16","arxiv_id":"2109.07983","n_code_links":0,"syntology":null},{"paper":"/paper/melt-message-level-transformer-with-masked","slug":"melt-message-level-transformer-with-masked","title":"MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection","date":"2021-09-16","arxiv_id":"2109.08113","n_code_links":1,"syntology":null},{"paper":"/paper/mover-mask-over-generate-and-rank-for","slug":"mover-mask-over-generate-and-rank-for","title":"MOVER: Mask, Over-generate and Rank for Hyperbole Generation","date":"2021-09-16","arxiv_id":"2109.07726","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrievalsum-a-retrieval-enhanced-framework","title":"RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization","date":"2021-09-16","arxiv_id":"2109.07943","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-tri-training-of-dependency-parsers","slug":"revisiting-tri-training-of-dependency-parsers","title":"Revisiting Tri-training of Dependency Parsers","date":"2021-09-16","arxiv_id":"2109.08122","n_code_links":2,"syntology":null},{"paper":null,"slug":"scaling-laws-for-neural-machine-translation","title":"Scaling Laws for Neural Machine Translation","date":"2021-09-16","arxiv_id":"2109.07740","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-factorization-of-large-square-matrices","slug":"sparse-factorization-of-large-square-matrices","title":"Sparse Factorization of Large Square Matrices","date":"2021-09-16","arxiv_id":"2109.08184","n_code_links":1,"syntology":null},{"paper":null,"slug":"tanet-a-new-paradigm-for-global-face-super","title":"TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network","date":"2021-09-16","arxiv_id":"2109.08174","n_code_links":0,"syntology":null},{"paper":"/paper/the-niutrans-system-for-the-wmt21-efficiency","slug":"the-niutrans-system-for-the-wmt21-efficiency","title":"The NiuTrans System for the WMT21 Efficiency Task","date":"2021-09-16","arxiv_id":"2109.08003","n_code_links":1,"syntology":null},{"paper":"/paper/the-niutrans-system-for-wngt-2020-efficiency-1","slug":"the-niutrans-system-for-wngt-2020-efficiency-1","title":"The NiuTrans System for WNGT 2020 Efficiency Task","date":"2021-09-16","arxiv_id":"2109.08008","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NiuTrans/NiuTrans.NMT","niutrans/niutensor"],"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":null,"slug":"utterance-level-neural-confidence-measure-for","title":"Utterance-level neural confidence measure for end-to-end children speech recognition","date":"2021-09-16","arxiv_id":"2109.07750","n_code_links":0,"syntology":null},{"paper":"/paper/anchor-detr-query-design-for-transformer","slug":"anchor-detr-query-design-for-transformer","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","date":"2021-09-15","arxiv_id":"2109.07107","n_code_links":2,"syntology":null},{"paper":"/paper/attention-is-indeed-all-you-need-semantically","slug":"attention-is-indeed-all-you-need-semantically","title":"Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG","date":"2021-09-15","arxiv_id":"2109.07043","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-is-robust-a-case-against-synonym-based","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","date":"2021-09-15","arxiv_id":"2109.07403","n_code_links":0,"syntology":null},{"paper":"/paper/e-fficient-bert-progressively-searching","slug":"e-fficient-bert-progressively-searching","title":"EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation","date":"2021-09-15","arxiv_id":"2109.07222","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["cheneydon/efficient-bert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"efficient-domain-adaptation-of-language","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","date":"2021-09-15","arxiv_id":"2109.07460","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-clinical-information-extraction","title":"Enhancing Clinical Information Extraction with Transferred Contextual Embeddings","date":"2021-09-15","arxiv_id":"2109.07243","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-local-global-transformer-for-image","slug":"hybrid-local-global-transformer-for-image","title":"Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing","date":"2021-09-15","arxiv_id":"2109.07100","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-text-auto-completion-with-next","title":"Improving Text Auto-Completion with Next Phrase Prediction","date":"2021-09-15","arxiv_id":"2109.07067","n_code_links":0,"syntology":null}],"record_sha256":"dd85612c06250fdadbfe4b637ca42d3393c00fd4149a3b485bdda15475f0412a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}