{"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/217","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":217,"pages_in_order":250,"rows_per_page":100,"rows":[21601,21700],"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/216","next":"/method/layer-normalization/papers/218","papers":[{"paper":"/paper/warp-word-level-adversarial-reprogramming","slug":"warp-word-level-adversarial-reprogramming","title":"WARP: Word-level Adversarial ReProgramming","date":"2021-01-01","arxiv_id":"2101.00121","n_code_links":1,"syntology":null},{"paper":null,"slug":"wb-detr-transformer-based-detector-without","title":"WB-DETR: Transformer-Based Detector Without Backbone","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-closer-look-at-few-shot-crosslingual","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","date":"2020-12-31","arxiv_id":"2012.15682","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-modal-deep-learning-model-for-video","title":"A Multi-modal Deep Learning Model for Video Thumbnail Selection","date":"2020-12-31","arxiv_id":"2101.00073","n_code_links":0,"syntology":null},{"paper":"/paper/better-robustness-by-more-coverage","slug":"better-robustness-by-more-coverage","title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning","date":"2020-12-31","arxiv_id":"2012.15699","n_code_links":1,"syntology":null},{"paper":"/paper/binarybert-pushing-the-limit-of-bert","slug":"binarybert-pushing-the-limit-of-bert","title":"BinaryBERT: Pushing the Limit of BERT Quantization","date":"2020-12-31","arxiv_id":"2012.15701","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"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","unlocated"]}}},{"paper":"/paper/cocolm-complex-commonsense-enhanced-language","slug":"cocolm-complex-commonsense-enhanced-language","title":"CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations","date":"2020-12-31","arxiv_id":"2012.15643","n_code_links":1,"syntology":null},{"paper":null,"slug":"conditional-generation-of-temporally-ordered","title":"Conditional Generation of Temporally-ordered Event Sequences","date":"2020-12-31","arxiv_id":"2012.15786","n_code_links":0,"syntology":null},{"paper":"/paper/directed-beam-search-plug-and-play-lexically","slug":"directed-beam-search-plug-and-play-lexically","title":"Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation","date":"2020-12-31","arxiv_id":"2012.15416","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dapascual/DirectedBeamSearch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/earlybert-efficient-bert-training-via-early-1","slug":"earlybert-efficient-bert-training-via-early-1","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","date":"2020-12-31","arxiv_id":"2101.00063","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["VITA-Group/EarlyBERT"],"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","unlocated"]}}},{"paper":"/paper/factual-error-correction-of-claims","slug":"factual-error-correction-of-claims","title":"Evidence-based Factual Error Correction","date":"2020-12-31","arxiv_id":"2012.15788","n_code_links":3,"syntology":null},{"paper":"/paper/fully-non-autoregressive-neural-machine","slug":"fully-non-autoregressive-neural-machine","title":"Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade","date":"2020-12-31","arxiv_id":"2012.15833","n_code_links":1,"syntology":null},{"paper":"/paper/kart-privacy-leakage-framework-of-language","slug":"kart-privacy-leakage-framework-of-language","title":"KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models","date":"2020-12-31","arxiv_id":"2101.00036","n_code_links":1,"syntology":null},{"paper":"/paper/linear-time-wordpiece-tokenization","slug":"linear-time-wordpiece-tokenization","title":"Fast WordPiece Tokenization","date":"2020-12-31","arxiv_id":"2012.15524","n_code_links":1,"syntology":null},{"paper":"/paper/making-pre-trained-language-models-better-few","slug":"making-pre-trained-language-models-better-few","title":"Making Pre-trained Language Models Better Few-shot Learners","date":"2020-12-31","arxiv_id":"2012.15723","n_code_links":9,"syntology":{"ran":2,"of":9,"n_ran_checked":2,"n_instrument":0,"unverified":7,"pointer_only":7,"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) · 7 unverified","official":{"repos":["princeton-nlp/LM-BFF"],"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/minilmv2-multi-head-self-attention-relation","slug":"minilmv2-multi-head-self-attention-relation","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","date":"2020-12-31","arxiv_id":"2012.15828","n_code_links":2,"syntology":null},{"paper":"/paper/rethinking-semantic-segmentation-from-a","slug":"rethinking-semantic-segmentation-from-a","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","date":"2020-12-31","arxiv_id":"2012.15840","n_code_links":5,"syntology":null},{"paper":null,"slug":"revisiting-robust-neural-machine-translation","title":"Revisiting Robust Neural Machine Translation: A Transformer Case Study","date":"2020-12-31","arxiv_id":"2012.15710","n_code_links":0,"syntology":null},{"paper":"/paper/shortformer-better-language-modeling-using","slug":"shortformer-better-language-modeling-using","title":"Shortformer: Better Language Modeling using Shorter Inputs","date":"2020-12-31","arxiv_id":"2012.15832","n_code_links":1,"syntology":null},{"paper":null,"slug":"studying-strategically-learning-to-mask-for","title":"Studying Strategically: Learning to Mask for Closed-book QA","date":"2020-12-31","arxiv_id":"2012.15856","n_code_links":0,"syntology":null},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"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":["EleutherAI/The-Pile"],"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/transtrack-multiple-object-tracking-with","slug":"transtrack-multiple-object-tracking-with","title":"TransTrack: Multiple Object Tracking with Transformer","date":"2020-12-31","arxiv_id":"2012.15460","n_code_links":2,"syntology":null},{"paper":"/paper/unified-mandarin-tts-front-end-based-on","slug":"unified-mandarin-tts-front-end-based-on","title":"Unified Mandarin TTS Front-end Based on Distilled BERT Model","date":"2020-12-31","arxiv_id":"2012.15404","n_code_links":1,"syntology":null},{"paper":"/paper/unks-everywhere-adapting-multilingual","slug":"unks-everywhere-adapting-multilingual","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","date":"2020-12-31","arxiv_id":"2012.15562","n_code_links":2,"syntology":null},{"paper":null,"slug":"verb-knowledge-injection-for-multilingual","title":"Verb Knowledge Injection for Multilingual Event Processing","date":"2020-12-31","arxiv_id":"2012.15421","n_code_links":0,"syntology":null},{"paper":null,"slug":"xlm-t-scaling-up-multilingual-machine","title":"XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders","date":"2020-12-31","arxiv_id":"2012.15547","n_code_links":0,"syntology":null},{"paper":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","n_code_links":2,"syntology":null},{"paper":null,"slug":"deriving-contextualised-semantic-features","title":"Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings","date":"2020-12-30","arxiv_id":"2012.15353","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-with-syntax-aware-local","slug":"improving-bert-with-syntax-aware-local","title":"Improving BERT with Syntax-aware Local Attention","date":"2020-12-30","arxiv_id":"2012.15150","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-deeper-transformers-on-small","slug":"optimizing-deeper-transformers-on-small","title":"Optimizing Deeper Transformers on Small Datasets","date":"2020-12-30","arxiv_id":"2012.15355","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-order-how-important-is-the-sequential","title":"Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?","date":"2020-12-30","arxiv_id":"2012.15180","n_code_links":0,"syntology":null},{"paper":"/paper/semglove-semantic-co-occurrences-for-glove","slug":"semglove-semantic-co-occurrences-for-glove","title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT","date":"2020-12-30","arxiv_id":"2012.15197","n_code_links":3,"syntology":null},{"paper":null,"slug":"transformer-for-image-quality-assessment","title":"Transformer for Image Quality Assessment","date":"2020-12-30","arxiv_id":"2101.01097","n_code_links":0,"syntology":null},{"paper":"/paper/unnatural-language-inference","slug":"unnatural-language-inference","title":"UnNatural Language Inference","date":"2020-12-30","arxiv_id":"2101.00010","n_code_links":1,"syntology":null},{"paper":"/paper/a-hierarchical-transformer-with-speaker","slug":"a-hierarchical-transformer-with-speaker","title":"A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation","date":"2020-12-29","arxiv_id":"2012.14781","n_code_links":1,"syntology":null},{"paper":"/paper/kaleidoscope-an-efficient-learnable-1","slug":"kaleidoscope-an-efficient-learnable-1","title":"Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps","date":"2020-12-29","arxiv_id":"2012.14966","n_code_links":2,"syntology":{"ran":16,"of":23,"n_ran_checked":9,"n_instrument":7,"unverified":7,"pointer_only":0,"phrase":"16 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","official":{"repos":["HazyResearch/butterfly","HazyResearch/learning-circuits"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":9,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","n_code_links":9,"syntology":null},{"paper":"/paper/robust-dialogue-utterance-rewriting-as","slug":"robust-dialogue-utterance-rewriting-as","title":"Robust Dialogue Utterance Rewriting as Sequence Tagging","date":"2020-12-29","arxiv_id":"2012.14535","n_code_links":1,"syntology":null},{"paper":"/paper/sit3-code-summarization-with-structure","slug":"sit3-code-summarization-with-structure","title":"Code Summarization with Structure-induced Transformer","date":"2020-12-29","arxiv_id":"2012.14710","n_code_links":1,"syntology":null},{"paper":"/paper/a-paragraph-level-multi-task-learning-model","slug":"a-paragraph-level-multi-task-learning-model","title":"A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification","date":"2020-12-28","arxiv_id":"2012.14500","n_code_links":1,"syntology":null},{"paper":null,"slug":"burt-bert-inspired-universal-representation-1","title":"BURT: BERT-inspired Universal Representation from Learning Meaningful Segment","date":"2020-12-28","arxiv_id":"2012.14320","n_code_links":0,"syntology":null},{"paper":"/paper/lattice-free-mmi-adaptation-of-self","slug":"lattice-free-mmi-adaptation-of-self","title":"Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models","date":"2020-12-28","arxiv_id":"2012.14252","n_code_links":2,"syntology":null},{"paper":"/paper/red-dragon-ai-at-textgraphs-2020-shared-task","slug":"red-dragon-ai-at-textgraphs-2020-shared-task","title":"Red Dragon AI at TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking","date":"2020-12-28","arxiv_id":"2012.14164","n_code_links":1,"syntology":null},{"paper":"/paper/syntax-enhanced-pre-trained-model","slug":"syntax-enhanced-pre-trained-model","title":"Syntax-Enhanced Pre-trained Model","date":"2020-12-28","arxiv_id":"2012.14116","n_code_links":1,"syntology":null},{"paper":"/paper/transpose-towards-explainable-human-pose","slug":"transpose-towards-explainable-human-pose","title":"TransPose: Keypoint Localization via Transformer","date":"2020-12-28","arxiv_id":"2012.14214","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-network-using-shared","title":"A multi-task learning network using shared BERT models for aspect-based sentiment analysis","date":"2020-12-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alp-kd-attention-based-layer-projection-for","title":"ALP-KD: Attention-Based Layer Projection for Knowledge Distillation","date":"2020-12-27","arxiv_id":"2012.14022","n_code_links":0,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-model-for-dialogue","slug":"an-embarrassingly-simple-model-for-dialogue","title":"An Embarrassingly Simple Model for Dialogue Relation Extraction","date":"2020-12-27","arxiv_id":"2012.13873","n_code_links":1,"syntology":null},{"paper":"/paper/inserting-information-bottlenecks-for","slug":"inserting-information-bottlenecks-for","title":"Inserting Information Bottlenecks for Attribution in Transformers","date":"2020-12-27","arxiv_id":"2012.13838","n_code_links":1,"syntology":null},{"paper":"/paper/learning-light-weight-translation-models-from","slug":"learning-light-weight-translation-models-from","title":"Learning Light-Weight Translation Models from Deep Transformer","date":"2020-12-27","arxiv_id":"2012.13866","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["libeineu/GPKD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/medal-medical-abbreviation-disambiguation","slug":"medal-medical-abbreviation-disambiguation","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","date":"2020-12-27","arxiv_id":"2012.13978","n_code_links":1,"syntology":null},{"paper":null,"slug":"portfolio-optimization-with-2d-relative","title":"Portfolio Optimization with 2D Relative-Attentional Gated Transformer","date":"2020-12-27","arxiv_id":"2101.03138","n_code_links":0,"syntology":null},{"paper":null,"slug":"sg-net-syntax-guided-transformer-for-language","title":"SG-Net: Syntax Guided Transformer for Language Representation","date":"2020-12-27","arxiv_id":"2012.13915","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-hateful-memes-using-a-multimodal","slug":"detecting-hateful-memes-using-a-multimodal","title":"Detecting Hateful Memes Using a Multimodal Deep Ensemble","date":"2020-12-24","arxiv_id":"2012.13235","n_code_links":1,"syntology":null},{"paper":"/paper/global-context-networks","slug":"global-context-networks","title":"Global Context Networks","date":"2020-12-24","arxiv_id":"2012.13375","n_code_links":3,"syntology":null},{"paper":null,"slug":"i-like-fish-especially-dolphins-addressing","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","date":"2020-12-24","arxiv_id":"2012.13391","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-based-model-agnostic-nlp","slug":"sentence-based-model-agnostic-nlp","title":"On the Granularity of Explanations in Model Agnostic NLP Interpretability","date":"2020-12-24","arxiv_id":"2012.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"to-what-extent-do-human-explanations-of-model","title":"To what extent do human explanations of model behavior align with actual model behavior?","date":"2020-12-24","arxiv_id":"2012.13354","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-visual-transformer","title":"A Survey on Visual Transformer","date":"2020-12-23","arxiv_id":"2012.12556","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","n_code_links":2,"syntology":null},{"paper":"/paper/detecting-hate-speech-in-memes-using","slug":"detecting-hate-speech-in-memes-using","title":"Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge","date":"2020-12-23","arxiv_id":"2012.12975","n_code_links":1,"syntology":null},{"paper":null,"slug":"future-guided-incremental-transformer-for","title":"Future-Guided Incremental Transformer for Simultaneous Translation","date":"2020-12-23","arxiv_id":"2012.12465","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-wav2vec2-0-to-speech-recognition-in","title":"Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages","date":"2020-12-22","arxiv_id":"2012.12121","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adaptation-of-nmt-models-for-english","title":"Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020","date":"2020-12-22","arxiv_id":"2012.12112","n_code_links":0,"syntology":null},{"paper":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","n_code_links":1,"syntology":null},{"paper":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","n_code_links":2,"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":["rabeehk/compacter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-retrieve-entity-aware-knowledge","slug":"learning-to-retrieve-entity-aware-knowledge","title":"Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems","date":"2020-12-22","arxiv_id":"2012.11937","n_code_links":1,"syntology":null},{"paper":null,"slug":"molecular-ct-unifying-geometry-and","title":"Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales","date":"2020-12-22","arxiv_id":"2012.11816","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-self-attention-with-role-guided","slug":"multi-head-self-attention-with-role-guided","title":"Multi-Head Self-Attention with Role-Guided Masks","date":"2020-12-22","arxiv_id":"2012.12366","n_code_links":1,"syntology":null},{"paper":"/paper/recognizing-emotion-cause-in-conversations-1","slug":"recognizing-emotion-cause-in-conversations-1","title":"Recognizing Emotion Cause in Conversations","date":"2020-12-22","arxiv_id":"2012.11820","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":"/paper/3d-object-detection-with-pointformer","slug":"3d-object-detection-with-pointformer","title":"3D Object Detection with Pointformer","date":"2020-12-21","arxiv_id":"2012.11409","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-graph-reasoning-network-for-multi-turn","title":"A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training","date":"2020-12-21","arxiv_id":"2012.11099","n_code_links":0,"syntology":null},{"paper":"/paper/cross-domain-retrieval-in-the-legal-and","slug":"cross-domain-retrieval-in-the-legal-and","title":"Cross-domain Retrieval in the Legal and Patent Domains: a Reproducibility Study","date":"2020-12-21","arxiv_id":"2012.11405","n_code_links":1,"syntology":null},{"paper":"/paper/domain-specific-bert-representation-for-named","slug":"domain-specific-bert-representation-for-named","title":"Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-12-21","arxiv_id":"2012.11145","n_code_links":1,"syntology":null},{"paper":null,"slug":"encoding-syntactic-knowledge-in-transformer","title":"Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling","date":"2020-12-21","arxiv_id":"2012.11689","n_code_links":0,"syntology":null},{"paper":"/paper/informer-transformer-likes-informed-attention","slug":"informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","n_code_links":5,"syntology":null},{"paper":"/paper/leveraging-parsbert-and-pretrained-mt5-for","slug":"leveraging-parsbert-and-pretrained-mt5-for","title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","date":"2020-12-21","arxiv_id":"2012.11204","n_code_links":1,"syntology":null},{"paper":"/paper/sub-linear-memory-how-to-make-performers-slim","slug":"sub-linear-memory-how-to-make-performers-slim","title":"Sub-Linear Memory: How to Make Performers SLiM","date":"2020-12-21","arxiv_id":"2012.11346","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-incorporating-entity-specific","title":"Towards Incorporating Entity-specific Knowledge Graph Information in Predicting Drug-Drug Interactions","date":"2020-12-21","arxiv_id":"2012.11142","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-bi-directional-attention-exploring","title":"Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension","date":"2020-12-20","arxiv_id":"2012.10877","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-using-pre-trained-bert","slug":"an-empirical-study-of-using-pre-trained-bert","title":"An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020","date":"2020-12-18","arxiv_id":"2012.10275","n_code_links":1,"syntology":null},{"paper":"/paper/hatexplain-a-benchmark-dataset-for","slug":"hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","arxiv_id":"2012.10289","n_code_links":6,"syntology":null},{"paper":"/paper/neurst-neural-speech-translation-toolkit","slug":"neurst-neural-speech-translation-toolkit","title":"NeurST: Neural Speech Translation Toolkit","date":"2020-12-18","arxiv_id":"2012.10018","n_code_links":1,"syntology":null},{"paper":"/paper/on-modality-bias-in-the-tvqa-dataset","slug":"on-modality-bias-in-the-tvqa-dataset","title":"On Modality Bias in the TVQA Dataset","date":"2020-12-18","arxiv_id":"2012.10210","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-streaming-asr-with-non-autoregressive","title":"Toward Streaming ASR with Non-Autoregressive Insertion-based Model","date":"2020-12-18","arxiv_id":"2012.10128","n_code_links":0,"syntology":null},{"paper":"/paper/a-generalization-of-transformer-networks-to","slug":"a-generalization-of-transformer-networks-to","title":"A Generalization of Transformer Networks to Graphs","date":"2020-12-17","arxiv_id":"2012.09699","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["graphdeeplearning/graphtransformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-white-box-analysis-of-colbert","title":"A White Box Analysis of ColBERT","date":"2020-12-17","arxiv_id":"2012.09650","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-shopping-comparing-distributional","slug":"bert-goes-shopping-comparing-distributional","title":"BERT Goes Shopping: Comparing Distributional Models for Product Representations","date":"2020-12-17","arxiv_id":"2012.09807","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-deep-object-tracking-with-circular","title":"End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box","date":"2020-12-17","arxiv_id":"2012.09771","n_code_links":0,"syntology":null},{"paper":"/paper/literature-retrieval-for-precision-medicine","slug":"literature-retrieval-for-precision-medicine","title":"Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization","date":"2020-12-17","arxiv_id":"2012.09355","n_code_links":1,"syntology":null},{"paper":"/paper/masker-masked-keyword-regularization-for","slug":"masker-masked-keyword-regularization-for","title":"MASKER: Masked Keyword Regularization for Reliable Text Classification","date":"2020-12-17","arxiv_id":"2012.09392","n_code_links":1,"syntology":null},{"paper":null,"slug":"mix-a-multi-task-learning-approach-to-solve","title":"MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering","date":"2020-12-17","arxiv_id":"2012.09766","n_code_links":0,"syntology":null},{"paper":"/paper/pct-point-cloud-transformer","slug":"pct-point-cloud-transformer","title":"PCT: Point cloud transformer","date":"2020-12-17","arxiv_id":"2012.09688","n_code_links":11,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["MenghaoGuo/PCT"],"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/sceneformer-indoor-scene-generation-with","slug":"sceneformer-indoor-scene-generation-with","title":"SceneFormer: Indoor Scene Generation with Transformers","date":"2020-12-17","arxiv_id":"2012.09793","n_code_links":2,"syntology":null},{"paper":"/paper/taming-transformers-for-high-resolution-image","slug":"taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","n_code_links":13,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CompVis/taming-transformers"],"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","unlocated"]}}},{"paper":null,"slug":"toward-transformer-based-object-detection","title":"Toward Transformer-Based Object Detection","date":"2020-12-17","arxiv_id":"2012.09958","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-interpretability-beyond-attention","slug":"transformer-interpretability-beyond-attention","title":"Transformer Interpretability Beyond Attention Visualization","date":"2020-12-17","arxiv_id":"2012.09838","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["hila-chefer/Transformer-Explainability"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/a-lightweight-neural-model-for-biomedical","slug":"a-lightweight-neural-model-for-biomedical","title":"A Lightweight Neural Model for Biomedical Entity Linking","date":"2020-12-16","arxiv_id":"2012.08844","n_code_links":1,"syntology":null}],"record_sha256":"0802e631715411fda5c1b28833f6087fc8b62f6c34eb6cd328282cc150d99f6b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}