{"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/189","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":189,"pages_in_order":250,"rows_per_page":100,"rows":[18801,18900],"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/188","next":"/method/layer-normalization/papers/190","papers":[{"paper":null,"slug":"replica-enhanced-feature-pyramid-network-by","title":"Lightweight Transformer Backbone for Medical Object Detection","date":"2021-11-22","arxiv_id":"2111.11546","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-vision-transformers","slug":"semi-supervised-vision-transformers","title":"Semi-Supervised Vision Transformers","date":"2021-11-22","arxiv_id":"2111.11067","n_code_links":1,"syntology":null},{"paper":null,"slug":"cpt-convolutional-point-transformer-for-3d","title":"CpT: Convolutional Point Transformer for 3D Point Cloud Processing","date":"2021-11-21","arxiv_id":"2111.10866","n_code_links":0,"syntology":null},{"paper":null,"slug":"dudotrans-dual-domain-transformer-provides","title":"DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction","date":"2021-11-21","arxiv_id":"2111.10790","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-softmax-approximation-for-deep","title":"Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism","date":"2021-11-21","arxiv_id":"2111.10770","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch","title":"Are Vision Transformers Robust to Patch Perturbations?","date":"2021-11-20","arxiv_id":"2111.10659","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-processing-matters-srph-konvergen-ai-s","title":"Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21","date":"2021-11-20","arxiv_id":"2111.10513","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-representations-strengthen-vision-1","slug":"discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","date":"2021-11-20","arxiv_id":"2111.10493","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-bert-look-at-sentiment-lexicon","title":"Does BERT look at sentiment lexicon?","date":"2021-11-19","arxiv_id":"2111.10100","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-graph-representation-learning-via-2","title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","date":"2021-11-19","arxiv_id":"2111.10447","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["frt03/generalized_dt"],"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":["unlocated"]}}},{"paper":"/paper/global-and-local-alignment-networks-for","slug":"global-and-local-alignment-networks-for","title":"Global and Local Alignment Networks for Unpaired Image-to-Image Translation","date":"2021-11-19","arxiv_id":"2111.10346","n_code_links":1,"syntology":null},{"paper":"/paper/grounded-situation-recognition-with","slug":"grounded-situation-recognition-with","title":"Grounded Situation Recognition with Transformers","date":"2021-11-19","arxiv_id":"2111.10135","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jhcho99/gsrtr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lexicon-based-methods-vs-bert-for-text","title":"Lexicon-based Methods vs. BERT for Text Sentiment Analysis","date":"2021-11-19","arxiv_id":"2111.10097","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-query-key-and-value-embedding-in","title":"Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints","date":"2021-11-19","arxiv_id":"2111.10017","n_code_links":0,"syntology":null},{"paper":"/paper/transmorph-transformer-for-unsupervised","slug":"transmorph-transformer-for-unsupervised","title":"TransMorph: Transformer for unsupervised medical image registration","date":"2021-11-19","arxiv_id":"2111.10480","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["junyuchen245/TransMorph_Transformer_for_Medical_Image_Registration"],"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":"zero-shot-certified-defense-against","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","date":"2021-11-19","arxiv_id":"2111.10481","n_code_links":0,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-tinybert-boost-tinybert-s-inference","title":"Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length","date":"2021-11-18","arxiv_id":"2111.09645","n_code_links":0,"syntology":null},{"paper":"/paper/how-emotionally-stable-is-albert-testing-1","slug":"how-emotionally-stable-is-albert-testing-1","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","date":"2021-11-18","arxiv_id":"2111.09612","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-much-do-language-models-copy-from-their","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","date":"2021-11-18","arxiv_id":"2111.09509","n_code_links":0,"syntology":null},{"paper":null,"slug":"lanobert-system-log-anomaly-detection-based","title":"LAnoBERT: System Log Anomaly Detection based on BERT Masked Language Model","date":"2021-11-18","arxiv_id":"2111.09564","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-on-ravdess","slug":"multimodal-emotion-recognition-on-ravdess","title":"Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning","date":"2021-11-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reference-based-magnetic-resonance-image","title":"Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer","date":"2021-11-18","arxiv_id":"2111.09492","n_code_links":0,"syntology":null},{"paper":"/paper/restormer-efficient-transformer-for-high","slug":"restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","arxiv_id":"2111.09881","n_code_links":13,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"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":{"repos":["swz30/restormer"],"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":["listed","official"]}}},{"paper":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","slug":"swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","n_code_links":23,"syntology":{"ran":17,"of":30,"n_ran_checked":17,"n_instrument":0,"unverified":13,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 3 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","official":{"repos":["microsoft/Swin-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":"/paper/the-power-of-selecting-key-blocks-with-local","slug":"the-power-of-selecting-key-blocks-with-local","title":"The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval","date":"2021-11-18","arxiv_id":"2111.09852","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-sample-almost-once-linear-cost-self-1","slug":"you-only-sample-almost-once-linear-cost-self-1","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","date":"2021-11-18","arxiv_id":"2111.09714","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mlpen/yoso"],"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":null,"slug":"guiding-generative-language-models-for-data","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","date":"2021-11-17","arxiv_id":"2111.09064","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-transfer-learning-and","title":"A Comparative Study on Transfer Learning and Distance Metrics in Semantic Clustering over the COVID-19 Tweets","date":"2021-11-16","arxiv_id":"2111.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-generative-xai-framework-for-natural","title":"A Deep Generative XAI Framework for Natural Language Inference Explanations Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-flexible-multi-task-model-for-bert-serving-1","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sentence-is-worth-128-pseudo-tokens-a","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structured-semantic-reinforcement-method","title":"A Structured Semantic Reinforcement method for Task-Oriented Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"active-dialogue-simulation-in-conversational","title":"Active Dialogue Simulation in Conversational Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adapler-speeding-up-inference-by-adaptive","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"all-birds-with-one-stone-multi-task-learning","title":"All Birds with One Stone: Multi-task Learning for Inference with One Forward Pass","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-document-to-document","title":"An Empirical Study of Document-to-document Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-information-theoretic-measurement-of","title":"An Information Theoretic Measurement of Topical Relevance in Learner Essays","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-isotropy-analysis-in-the-multilingual-bert-1","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"anna-enhanced-language-representation-for","title":"ANNA: Enhanced Language Representation for Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-coherence-modeling-capabilities","title":"Assessing the Coherence Modeling Capabilities of Pretrained Transformer-based Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attention-based-multi-hypothesis-fusion-for","slug":"attention-based-multi-hypothesis-fusion-for","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","date":"2021-11-16","arxiv_id":"2111.08201","n_code_links":2,"syntology":null},{"paper":null,"slug":"barcor-towards-a-unified-framework-for","title":"BARCOR: Towards A Unified Framework for Conversational Recommendation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-got-a-date-introducing-transformers-to-1","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-is-robust-a-case-against-synonym-based-1","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bigfive-a-dataset-of-coarse-and-fine-grained","title":"BigFive: A Dataset of Coarse- and Fine-Grained Personality Characteristics","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bort-back-and-denoising-reconstruction-for","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models-1","slug":"building-chinese-biomedical-language-models-1","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"calbert-code-mixed-adaptive-language","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-transformers-improving-the-robustness","title":"Causal Transformers: Improving the Robustness on Spurious Correlations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"challenges-for-open-domain-targeted-sentiment","title":"Challenges for Open-domain Targeted Sentiment Analysis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"chinese-word-attention-based-on-valid","title":"Chinese Word Attention based on Valid Division of Sentence","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"coloring-the-blank-slate-pre-training-imparts","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-sentence-representation-via","title":"Compressing Sentence Representation via Homomorphic Projective Distillation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"constructing-phrase-level-semantic-labels-to-1","title":"Constructing Phrase-level Semantic Labels to Form Multi-GrainedSupervision for Image-Text Retrieval","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-sensorimotor-norms-multi","title":"Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"create-a-benchmark-for-chinese-short-video","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-named-entity-recognition-via","title":"Cross-domain Named Entity Recognition via Graph Matching","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cst5-data-augmentation-for-code-switched","title":"CST5: Data augmentation for Code-Switched Semantic Parsing","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cvss-bert-explainable-natural-language","slug":"cvss-bert-explainable-natural-language","title":"CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description","date":"2021-11-16","arxiv_id":"2111.08510","n_code_links":1,"syntology":null},{"paper":null,"slug":"daml-st5-low-resource-style-transfer-via","title":"DAML-ST5: Low Resource Style Transfer via Domain Adaptive Meta Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-and-learned-layer","title":"Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-for-intent-classification","title":"Data Augmentation for Intent Classification with Generic Large Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-contamination-from-memorization-to","title":"Data Contamination: From Memorization to Exploitation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dawson-data-augmentation-using-weak","title":"DAWSON: Data Augmentation using Weak Supervision On Natural Language","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-to-bottom-weights-decay-a-systemic","title":"Deep-to-bottom Weights Decay: A Systemic Knowledge Review Learning Technique for Transformer Layers in Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"discontinuous-constituency-and-bert-a-case","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-long-sequence-encoding-via","title":"Efficient Long Sequence Encoding via Synchronization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eliteplm-an-empirical-study-on-general","title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elle-efficient-lifelong-pre-training-for","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-analysis-of-training-strategies-of-1","title":"Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-sign-language-translation-via","title":"End-To-End Sign Language Translation via Multitask Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-task-oriented-dialog-policy","title":"End-to-end Task-oriented Dialog Policy Learning based on Pre-trained Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-nonlinear-mutual-dependencies","title":"Enhancing the Nonlinear Mutual Dependencies in Transformers with Mutual Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-learning-hierarchical-efficient","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-detection-via-derangement-question","title":"Event Detection via Derangement Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eventbert","title":"EventBERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"explicit-modeling-the-context-for-chinese-ner","title":"Explicit Modeling the Context for Chinese NER","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-adapting-chinese-gpt-to-pinyin","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-multi-label-text-classification-with-1","title":"Extreme Multi-label Text Classification with Multi-layer Experts","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-gaze-and-self-attention-how-humans-and","title":"Eye Gaze and Self-attention: How Humans and Transformers Attend Words in Sentences","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-transformer-based","title":"Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-rich-open-vocabulary-interpretable","title":"Feature-rich Open-vocabulary Interpretable Neural Representations for All of the World’s 7000 Languages","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-structure-distillation-for-bert","title":"Feature Structure Distillation for BERT Transferring","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fix-bugs-with-transformer-through-a-neural","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"frsum-towards-faithful-abstractive","title":"FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gabert-an-irish-language-model-1","title":"gaBERT — an Irish Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-diverse-and-high-quality","title":"Generating Diverse and High-Quality Abstractive Summaries with Variational Transformers","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-of-news-articles-from-tweets-an","title":"Generation of News Articles from Tweets : An Experiment","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-design","title":"Generative Pre-Trained Transformer for Design Concept Generation: An Exploration","date":"2021-11-16","arxiv_id":"2111.08489","n_code_links":0,"syntology":null},{"paper":null,"slug":"get-the-point-graph-enhanced-candidate","title":"Get the Point! Graph Enhanced Candidate Retrieval for Zero-shot Entity Linking","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"glm-general-language-model-pretraining-with","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-based-fine-grained-multimodal-attention","title":"Graph-based Fine-grained Multimodal Attention Mechanism for Sentiment Analysis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-the-pre-training-objective-affect","title":"How does the pre-training objective affect what large language models learn about linguistic properties?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"0d7c9e0be415f7395542b9ceb680de1652d11e257d841d0786f4496deb29448a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}