{"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/193","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":193,"pages_in_order":250,"rows_per_page":100,"rows":[19201,19300],"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/192","next":"/method/layer-normalization/papers/194","papers":[{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/prix-lm-pretraining-for-multilingual","slug":"prix-lm-pretraining-for-multilingual","title":"Prix-LM: Pretraining for Multilingual Knowledge Base Construction","date":"2021-10-16","arxiv_id":"2110.08443","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-search-as-extractive-paraphrase-span","title":"Semantic Search as Extractive Paraphrase Span Detection","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-improves","title":"Sharpness-Aware Minimization Improves Language Model Generalization","date":"2021-10-16","arxiv_id":"2110.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"should-we-trust-this-summary-bayesian","title":"Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spellm-augmenting-chinese-spell-check-using","title":"SpelLM: Augmenting Chinese Spell Check Using Input Salience","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-10-16","arxiv_id":"2110.08525","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-with-a-mixture-of-gaussian-keys-1","slug":"transformer-with-a-mixture-of-gaussian-keys-1","title":"Improving Transformers with Probabilistic Attention Keys","date":"2021-10-16","arxiv_id":"2110.08678","n_code_links":1,"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: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minhtannguyen/transformer-mgk"],"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":"wechsel-effective-initialization-of-subword","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-do-compressed-large-language-models","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","date":"2021-10-16","arxiv_id":"2110.08419","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-cnns-with-transformer-for","title":"Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining","date":"2021-10-15","arxiv_id":"2110.07919","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-gender-bias-in-transformer-based","title":"Detecting Gender Bias in Transformer-based Models: A Case Study on BERT","date":"2021-10-15","arxiv_id":"2110.15733","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-faithfulness-of-importance","slug":"evaluating-the-faithfulness-of-importance","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","date":"2021-10-15","arxiv_id":"2110.08412","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["AndreasMadsen/nlp-roar-interpretability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-natural-language-adversarial-1","title":"Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm","date":"2021-10-15","arxiv_id":"2110.08036","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-curriculum-learning-for-amr","slug":"hierarchical-curriculum-learning-for-amr","title":"Hierarchical Curriculum Learning for AMR Parsing","date":"2021-10-15","arxiv_id":"2110.07855","n_code_links":1,"syntology":null},{"paper":null,"slug":"intent-based-product-collections-for-e","title":"Intent-based Product Collections for E-commerce using Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08241","n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","n_code_links":0,"syntology":null},{"paper":"/paper/on-learning-the-transformer-kernel-1","slug":"on-learning-the-transformer-kernel-1","title":"On Learning the Transformer Kernel","date":"2021-10-15","arxiv_id":"2110.08323","n_code_links":1,"syntology":null},{"paper":"/paper/probing-as-quantifying-the-inductive-bias-of","slug":"probing-as-quantifying-the-inductive-bias-of","title":"Probing as Quantifying Inductive Bias","date":"2021-10-15","arxiv_id":"2110.08388","n_code_links":1,"syntology":null},{"paper":null,"slug":"streamult-streaming-multimodal-transformer","title":"StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data","date":"2021-10-15","arxiv_id":"2110.08021","n_code_links":0,"syntology":null},{"paper":"/paper/tracing-origins-coref-aware-machine-reading","slug":"tracing-origins-coref-aware-machine-reading","title":"Tracing Origins: Coreference-aware Machine Reading Comprehension","date":"2021-10-15","arxiv_id":"2110.07961","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-strong-and-robust-baseline-for","slug":"a-simple-strong-and-robust-baseline-for","title":"PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction","date":"2021-10-14","arxiv_id":"2110.07415","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2bert-towards-reusable-pretrained","title":"bert2BERT: Towards Reusable Pretrained Language Models","date":"2021-10-14","arxiv_id":"2110.07143","n_code_links":0,"syntology":null},{"paper":"/paper/bi-rads-bert-using-section-tokenization-to","slug":"bi-rads-bert-using-section-tokenization-to","title":"BI-RADS BERT & Using Section Segmentation to Understand Radiology Reports","date":"2021-10-14","arxiv_id":"2110.07552","n_code_links":1,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models","slug":"building-chinese-biomedical-language-models","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-10-14","arxiv_id":"2110.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-transformers-perform-below-chance-on","title":"Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans","date":"2021-10-14","arxiv_id":"2110.07240","n_code_links":0,"syntology":null},{"paper":null,"slug":"causally-estimating-the-sensitivity-of-neural-1","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-10-14","arxiv_id":"2110.07159","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-gloss-augmentation-for-improving-word","title":"Context-gloss Augmentation for Improving Word Sense Disambiguation","date":"2021-10-14","arxiv_id":"2110.07174","n_code_links":0,"syntology":null},{"paper":"/paper/delphi-towards-machine-ethics-and-norms","slug":"delphi-towards-machine-ethics-and-norms","title":"Can Machines Learn Morality? The Delphi Experiment","date":"2021-10-14","arxiv_id":"2110.07574","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-off-the-shelf-machine-listening","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","date":"2021-10-14","arxiv_id":"2110.07410","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolutionary-trajectory-and-origin-of-sars","title":"Integrating Fréchet distance and AI reveals the evolutionary trajectory and origin of SARS-CoV-2","date":"2021-10-14","arxiv_id":"2110.07696","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-timbre-disentanglement-in-non","title":"Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech","date":"2021-10-14","arxiv_id":"2110.07192","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-introductions-in-podcast-episodes","slug":"identifying-introductions-in-podcast-episodes","title":"Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts","date":"2021-10-14","arxiv_id":"2110.07096","n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-drug-target-interaction-prediction","title":"Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer","date":"2021-10-14","arxiv_id":"2110.07347","n_code_links":0,"syntology":null},{"paper":"/paper/lfpt5-a-unified-framework-for-lifelong-few-1","slug":"lfpt5-a-unified-framework-for-lifelong-few-1","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","date":"2021-10-14","arxiv_id":"2110.07298","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["qcwthu/lifelong-fewshot-language-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mofe-mixture-of-factual-experts-for-1","title":"CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization","date":"2021-10-14","arxiv_id":"2110.07166","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-translation-with-layer","slug":"non-autoregressive-translation-with-layer","title":"Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision","date":"2021-10-14","arxiv_id":"2110.07515","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["chenyangh/dslp"],"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/p-adapters-robustly-extracting-factual-1","slug":"p-adapters-robustly-extracting-factual-1","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","date":"2021-10-14","arxiv_id":"2110.07280","n_code_links":1,"syntology":null},{"paper":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","n_code_links":6,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["microsoft/speecht5"],"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/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","n_code_links":0,"syntology":null},{"paper":"/paper/symbolic-knowledge-distillation-from-general","slug":"symbolic-knowledge-distillation-from-general","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","date":"2021-10-14","arxiv_id":"2110.07178","n_code_links":1,"syntology":null},{"paper":"/paper/the-neural-data-router-adaptive-control-flow","slug":"the-neural-data-router-adaptive-control-flow","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-10-14","arxiv_id":"2110.07732","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["robertcsordas/ndr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-for-polyp-detection","title":"Transformer for Polyp Detection","date":"2021-10-14","arxiv_id":"2111.07918","n_code_links":0,"syntology":null},{"paper":null,"slug":"clip4caption-clip-for-video-caption","title":"CLIP4Caption: CLIP for Video Caption","date":"2021-10-13","arxiv_id":"2110.06615","n_code_links":0,"syntology":null},{"paper":null,"slug":"covert-message-passing-over-public-internet","title":"Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for \"Dead-Drop\" Deployments","date":"2021-10-13","arxiv_id":"2110.07009","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-in-spanish-using-deep","slug":"fake-news-detection-in-spanish-using-deep","title":"Fake News Detection in Spanish Using Deep Learning Techniques","date":"2021-10-13","arxiv_id":"2110.06461","n_code_links":1,"syntology":null},{"paper":"/paper/improving-graph-based-sentence-ordering-with","slug":"improving-graph-based-sentence-ordering-with","title":"Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings","date":"2021-10-13","arxiv_id":"2110.06446","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["deeplearnxmu/irseg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"language-modelling-via-learning-to-rank","title":"Language Modelling via Learning to Rank","date":"2021-10-13","arxiv_id":"2110.06961","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-redundancy-in-attention-with-reuse-1","slug":"leveraging-redundancy-in-attention-with-reuse-1","title":"Leveraging redundancy in attention with Reuse Transformers","date":"2021-10-13","arxiv_id":"2110.06821","n_code_links":1,"syntology":null},{"paper":null,"slug":"maximizing-efficiency-of-language-model-pre","title":"Maximizing Efficiency of Language Model Pre-training for Learning Representation","date":"2021-10-13","arxiv_id":"2110.06620","n_code_links":0,"syntology":null},{"paper":"/paper/mderank-a-masked-document-embedding-rank","slug":"mderank-a-masked-document-embedding-rank","title":"MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction","date":"2021-10-13","arxiv_id":"2110.06651","n_code_links":1,"syntology":null},{"paper":null,"slug":"multistage-linguistic-conditioning-of","title":"Multistage linguistic conditioning of convolutional layers for speech emotion recognition","date":"2021-10-13","arxiv_id":"2110.06650","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-for-the-few-shot-adaptation-of-1","title":"Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers","date":"2021-10-13","arxiv_id":"2110.06990","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantics-aware-attention-improves-neural","title":"Semantics-aware Attention Improves Neural Machine Translation","date":"2021-10-13","arxiv_id":"2110.06920","n_code_links":0,"syntology":null},{"paper":"/paper/study-of-positional-encoding-approaches-for","slug":"study-of-positional-encoding-approaches-for","title":"Study of positional encoding approaches for Audio Spectrogram Transformers","date":"2021-10-13","arxiv_id":"2110.06999","n_code_links":1,"syntology":null},{"paper":"/paper/the-dawn-of-quantum-natural-language","slug":"the-dawn-of-quantum-natural-language","title":"The Dawn of Quantum Natural Language Processing","date":"2021-10-13","arxiv_id":"2110.06510","n_code_links":2,"syntology":null},{"paper":"/paper/towards-efficient-nlp-a-standard-evaluation","slug":"towards-efficient-nlp-a-standard-evaluation","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","date":"2021-10-13","arxiv_id":"2110.07038","n_code_links":1,"syntology":null},{"paper":null,"slug":"transform-and-bitstream-domain-image","title":"Transform and Bitstream Domain Image Classification","date":"2021-10-13","arxiv_id":"2110.06740","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-of-emotion-perception-from-art","title":"Understanding of Emotion Perception from Art","date":"2021-10-13","arxiv_id":"2110.06486","n_code_links":0,"syntology":null},{"paper":"/paper/yformer-u-net-inspired-transformer-1","slug":"yformer-u-net-inspired-transformer-1","title":"Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting","date":"2021-10-13","arxiv_id":"2110.08255","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-scale-lexical-and-semantic-analysis","title":"Regionalized models for Spanish language variations based on Twitter","date":"2021-10-12","arxiv_id":"2110.06128","n_code_links":0,"syntology":null},{"paper":null,"slug":"all-dolphins-are-intelligent-and-some-are","title":"ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality","date":"2021-10-12","arxiv_id":"2110.06376","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-guided-generative-models-for","title":"Attention-guided Generative Models for Extractive Question Answering","date":"2021-10-12","arxiv_id":"2110.06393","n_code_links":0,"syntology":null},{"paper":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","n_code_links":2,"syntology":null},{"paper":"/paper/contrastive-learning-for-representation","slug":"contrastive-learning-for-representation","title":"Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation","date":"2021-10-12","arxiv_id":"2110.05730","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["RuihongQiu/DuoRec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/discodvt-generating-long-text-with-discourse","slug":"discodvt-generating-long-text-with-discourse","title":"DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer","date":"2021-10-12","arxiv_id":"2110.05999","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-inference-with-neural-interpreters","title":"Dynamic Inference with Neural Interpreters","date":"2021-10-12","arxiv_id":"2110.06399","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-feelings-of-people-regarding-covid","title":"Extracting Feelings of People Regarding COVID-19 by Social Network Mining","date":"2021-10-12","arxiv_id":"2110.06151","n_code_links":0,"syntology":null},{"paper":"/paper/hetformer-heterogeneous-transformer-with","slug":"hetformer-heterogeneous-transformer-with","title":"HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization","date":"2021-10-12","arxiv_id":"2110.06388","n_code_links":1,"syntology":null},{"paper":"/paper/lightseq-accelerated-training-for-transformer","slug":"lightseq-accelerated-training-for-transformer","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","date":"2021-10-12","arxiv_id":"2110.05722","n_code_links":1,"syntology":null},{"paper":"/paper/list-lite-self-training-makes-efficient-few-1","slug":"list-lite-self-training-makes-efficient-few-1","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","date":"2021-10-12","arxiv_id":"2110.06274","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/list"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mention-memory-incorporating-textual-1","slug":"mention-memory-incorporating-textual-1","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","date":"2021-10-12","arxiv_id":"2110.06176","n_code_links":1,"syntology":null},{"paper":"/paper/relative-molecule-self-attention-transformer-1","slug":"relative-molecule-self-attention-transformer-1","title":"Relative Molecule Self-Attention Transformer","date":"2021-10-12","arxiv_id":"2110.05841","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/rescoring-sequence-to-sequence-models-for","slug":"rescoring-sequence-to-sequence-models-for","title":"Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes","date":"2021-10-12","arxiv_id":"2110.05909","n_code_links":1,"syntology":null},{"paper":"/paper/satellite-image-semantic-segmentation","slug":"satellite-image-semantic-segmentation","title":"Satellite Image Semantic Segmentation","date":"2021-10-12","arxiv_id":"2110.05812","n_code_links":1,"syntology":null},{"paper":"/paper/starformer-transformer-with-state-action-1","slug":"starformer-transformer-with-state-action-1","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","date":"2021-10-12","arxiv_id":"2110.06206","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["elicassion/StARformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptively-multi-view-and-temporal-fusing","slug":"adaptively-multi-view-and-temporal-fusing","title":"Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation","date":"2021-10-11","arxiv_id":"2110.05092","n_code_links":0,"syntology":null},{"paper":"/paper/certified-patch-robustness-via-smoothed-1","slug":"certified-patch-robustness-via-smoothed-1","title":"Certified Patch Robustness via Smoothed Vision Transformers","date":"2021-10-11","arxiv_id":"2110.07719","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["madrylab/smoothed-vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-gender-fairness-of-pre-trained-1","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","date":"2021-10-11","arxiv_id":"2110.05367","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-transfer-learning-capabilities","slug":"investigating-transfer-learning-capabilities","title":"Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block","date":"2021-10-11","arxiv_id":"2110.05270","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-for-situated-multi-domain","title":"Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems","date":"2021-10-11","arxiv_id":"2110.05221","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-self-attention-based-transformer","title":"Multi-View Self-Attention Based Transformer for Speaker Recognition","date":"2021-10-11","arxiv_id":"2110.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"offensive-language-detection-with-bert-based","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","date":"2021-10-11","arxiv_id":"2110.05133","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-variable-training-for-efficient-on","title":"Partial Variable Training for Efficient On-Device Federated Learning","date":"2021-10-11","arxiv_id":"2110.05607","n_code_links":0,"syntology":null},{"paper":null,"slug":"sru-pioneering-fast-recurrence-with-attention","title":"SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition","date":"2021-10-11","arxiv_id":"2110.05571","n_code_links":0,"syntology":null},{"paper":"/paper/topic-modeling-clade-assisted-sentiment","slug":"topic-modeling-clade-assisted-sentiment","title":"Topic Modeling, Clade-assisted Sentiment Analysis, and Vaccine Brand Reputation Analysis of COVID-19 Vaccine-related Facebook Comments in the Philippines","date":"2021-10-11","arxiv_id":"2111.04416","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-source-separation-via-bayesian","slug":"unsupervised-source-separation-via-bayesian","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","date":"2021-10-11","arxiv_id":"2110.05313","n_code_links":1,"syntology":null},{"paper":null,"slug":"dct-dynamic-compressive-transformer-for","title":"DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence","date":"2021-10-10","arxiv_id":"2110.04821","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-channel-end-to-end-neural-diarization","title":"Multi-Channel End-to-End Neural Diarization with Distributed Microphones","date":"2021-10-10","arxiv_id":"2110.04694","n_code_links":0,"syntology":null},{"paper":"/paper/nvit-vision-transformer-compression-and-1","slug":"nvit-vision-transformer-compression-and-1","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","date":"2021-10-10","arxiv_id":"2110.04869","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"on-automatic-text-extractive-summarization","title":"Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention","date":"2021-10-10","arxiv_id":"2110.04878","n_code_links":0,"syntology":null},{"paper":"/paper/paste-a-tagging-free-decoding-framework-using","slug":"paste-a-tagging-free-decoding-framework-using","title":"PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction","date":"2021-10-10","arxiv_id":"2110.04794","n_code_links":1,"syntology":null},{"paper":"/paper/sp-gpt2-semantics-improvement-in-vietnamese","slug":"sp-gpt2-semantics-improvement-in-vietnamese","title":"SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation","date":"2021-10-10","arxiv_id":"2110.15723","n_code_links":2,"syntology":null},{"paper":null,"slug":"supershaper-task-agnostic-super-pre-training","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","date":"2021-10-10","arxiv_id":"2110.04711","n_code_links":0,"syntology":null},{"paper":"/paper/yuan-1-0-large-scale-pre-trained-language","slug":"yuan-1-0-large-scale-pre-trained-language","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","date":"2021-10-10","arxiv_id":"2110.04725","n_code_links":1,"syntology":null},{"paper":"/paper/an-isotropy-analysis-in-the-multilingual-bert","slug":"an-isotropy-analysis-in-the-multilingual-bert","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","date":"2021-10-09","arxiv_id":"2110.04504","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-recent-advances-in-pre-trained","slug":"leveraging-recent-advances-in-pre-trained","title":"Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction","date":"2021-10-09","arxiv_id":"2110.04475","n_code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-image-modeling-with-improved-1","slug":"vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/vision-transformer-based-covid-19-detection","slug":"vision-transformer-based-covid-19-detection","title":"Vision Transformer based COVID-19 Detection using Chest X-rays","date":"2021-10-09","arxiv_id":"2110.04458","n_code_links":0,"syntology":null}],"record_sha256":"668e4d7c624b3f1908bffd9f2f45d914abcb2a9956a24cbf10a846108b6c0a6f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}