{"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/multi-head-attention/papers/211","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","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":211,"pages_in_order":249,"rows_per_page":100,"rows":[21001,21100],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/210","next":"/method/multi-head-attention/papers/212","papers":[{"paper":null,"slug":"thinking-aloud-dynamic-context-generation","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","date":"2021-03-24","arxiv_id":"2103.13033","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformers-for-dense-prediction","slug":"vision-transformers-for-dense-prediction","title":"Vision Transformers for Dense Prediction","date":"2021-03-24","arxiv_id":"2103.13413","n_code_links":15,"syntology":{"ran":65,"of":116,"n_ran_checked":32,"n_instrument":33,"unverified":51,"pointer_only":15,"phrase":"65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified","official":null}},{"paper":"/paper/are-neural-language-models-good-plagiarists-a","slug":"are-neural-language-models-good-plagiarists-a","title":"Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection","date":"2021-03-23","arxiv_id":"2103.12450","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-hate-speech-with-gpt-3","slug":"detecting-hate-speech-with-gpt-3","title":"Detecting Hate Speech with GPT-3","date":"2021-03-23","arxiv_id":"2103.12407","n_code_links":2,"syntology":null},{"paper":null,"slug":"repairing-pronouns-in-translation-with-bert","title":"Repairing Pronouns in Translation with BERT-Based Post-Editing","date":"2021-03-23","arxiv_id":"2103.12838","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nlp-cookbook-modern-recipes-for","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","date":"2021-03-23","arxiv_id":"2104.10640","n_code_links":0,"syntology":null},{"paper":null,"slug":"tmr-evaluating-ner-recall-on-tough-mentions","title":"TMR: Evaluating NER Recall on Tough Mentions","date":"2021-03-23","arxiv_id":"2103.12312","n_code_links":0,"syntology":null},{"paper":null,"slug":"variable-name-recovery-in-decompiled-binary","title":"Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling","date":"2021-03-23","arxiv_id":"2103.12801","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-a-review-of-applications-in-natural","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","date":"2021-03-22","arxiv_id":"2103.11943","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-between-supervised","title":"Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management","date":"2021-03-22","arxiv_id":"2103.11835","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-trainable-multi-instance-pose","slug":"end-to-end-trainable-multi-instance-pose","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","date":"2021-03-22","arxiv_id":"2103.12115","n_code_links":2,"syntology":{"ran":15,"of":18,"n_ran_checked":13,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["amathislab/poet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/hybrid-model-for-patent-classification-using","slug":"hybrid-model-for-patent-classification-using","title":"PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT","date":"2021-03-22","arxiv_id":"2103.11933","n_code_links":2,"syntology":null},{"paper":"/paper/identifying-machine-paraphrased-plagiarism","slug":"identifying-machine-paraphrased-plagiarism","title":"Identifying Machine-Paraphrased Plagiarism","date":"2021-03-22","arxiv_id":"2103.11909","n_code_links":2,"syntology":null},{"paper":"/paper/incorporating-convolution-designs-into-visual","slug":"incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","arxiv_id":"2103.11816","n_code_links":3,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result","official":{"repos":["coeusguo/ceit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/meta-detr-few-shot-object-detection-via","slug":"meta-detr-few-shot-object-detection-via","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","date":"2021-03-22","arxiv_id":"2103.11731","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhangGongjie/Meta-DETR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-domain-question-answering-over-tables","slug":"open-domain-question-answering-over-tables","title":"Open Domain Question Answering over Tables via Dense Retrieval","date":"2021-03-22","arxiv_id":"2103.12011","n_code_links":1,"syntology":null},{"paper":"/paper/tiny-transformers-for-environmental-sound","slug":"tiny-transformers-for-environmental-sound","title":"Tiny Transformers for Environmental Sound Classification at the Edge","date":"2021-03-22","arxiv_id":"2103.12157","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-unsupervised-sampling-approach-for-image","title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information","date":"2021-03-21","arxiv_id":"2104.02605","n_code_links":0,"syntology":null},{"paper":null,"slug":"maast-map-attention-with-semantic","title":"MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation","date":"2021-03-21","arxiv_id":"2103.11374","n_code_links":0,"syntology":null},{"paper":null,"slug":"namerec-highly-accurate-and-fine-grained","title":"NameRec*: Highly Accurate and Fine-grained Person Name Recognition","date":"2021-03-21","arxiv_id":"2103.11360","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-translation-by-learning","slug":"non-autoregressive-translation-by-learning","title":"Non-Autoregressive Translation by Learning Target Categorical Codes","date":"2021-03-21","arxiv_id":"2103.11405","n_code_links":1,"syntology":null},{"paper":null,"slug":"paying-attention-to-activation-maps-in-camera","title":"Paying Attention to Activation Maps in Camera Pose Regression","date":"2021-03-21","arxiv_id":"2103.11477","n_code_links":0,"syntology":null},{"paper":"/paper/rosita-refined-bert-compression-with","slug":"rosita-refined-bert-compression-with","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","date":"2021-03-21","arxiv_id":"2103.11367","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["llyx97/Rosita"],"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/paying-attention-to-multiscale-feature-maps","slug":"paying-attention-to-multiscale-feature-maps","title":"Attention-Based Multimodal Image Matching","date":"2021-03-20","arxiv_id":"2103.11247","n_code_links":1,"syntology":null},{"paper":null,"slug":"api2com-on-the-improvement-of-automatically","title":"API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentations","date":"2021-03-19","arxiv_id":"2103.10668","n_code_links":0,"syntology":null},{"paper":"/paper/convit-improving-vision-transformers-with","slug":"convit-improving-vision-transformers-with","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","date":"2021-03-19","arxiv_id":"2103.10697","n_code_links":9,"syntology":null},{"paper":null,"slug":"cost-effective-deployment-of-bert-models-in","title":"Cost-effective Deployment of BERT Models in Serverless Environment","date":"2021-03-19","arxiv_id":"2103.10673","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-attention-recurrent-neural-networks-for","title":"Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version","date":"2021-03-19","arxiv_id":"2103.10760","n_code_links":0,"syntology":null},{"paper":"/paper/hopper-multi-hop-transformer-for-1","slug":"hopper-multi-hop-transformer-for-1","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","date":"2021-03-19","arxiv_id":"2103.10574","n_code_links":1,"syntology":null},{"paper":"/paper/let-your-heart-speak-in-its-mother-tongue","slug":"let-your-heart-speak-in-its-mother-tongue","title":"Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals","date":"2021-03-19","arxiv_id":"2103.11011","n_code_links":1,"syntology":null},{"paper":"/paper/muril-multilingual-representations-for-indian","slug":"muril-multilingual-representations-for-indian","title":"MuRIL: Multilingual Representations for Indian Languages","date":"2021-03-19","arxiv_id":"2103.10730","n_code_links":1,"syntology":null},{"paper":null,"slug":"play-the-shannon-game-with-language-models-a","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","date":"2021-03-19","arxiv_id":"2103.10918","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-visual-transformers-with","slug":"scalable-visual-transformers-with","title":"Scalable Vision Transformers with Hierarchical Pooling","date":"2021-03-19","arxiv_id":"2103.10619","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["MonashAI/HVT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transferable-model-for-shape-optimization","title":"Transferable Model for Shape Optimization subject to Physical Constraints","date":"2021-03-19","arxiv_id":"2103.10805","n_code_links":0,"syntology":null},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","n_code_links":8,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"contextual-biasing-of-language-models-for","title":"Contextual Biasing of Language Models for Speech Recognition in Goal-Oriented Conversational Agents","date":"2021-03-18","arxiv_id":"2103.10325","n_code_links":0,"syntology":null},{"paper":"/paper/danish-fungi-2020-not-just-another-image","slug":"danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-transformer-for-video-understanding","title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training","date":"2021-03-18","arxiv_id":"2103.10043","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","n_code_links":10,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/P-tuning"],"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":["listed","official"]}}},{"paper":"/paper/model-extraction-and-adversarial","slug":"model-extraction-and-adversarial","title":"Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!","date":"2021-03-18","arxiv_id":"2103.10013","n_code_links":1,"syntology":null},{"paper":null,"slug":"spices-survey-papers-as-interactive","title":"SPICES: SURVEY PAPERS AS INTERACTIVE CHEATSHEET EMBEDDINGS","date":"2021-03-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unetr-transformers-for-3d-medical-image","slug":"unetr-transformers-for-3d-medical-image","title":"UNETR: Transformers for 3D Medical Image Segmentation","date":"2021-03-18","arxiv_id":"2103.10504","n_code_links":10,"syntology":null},{"paper":null,"slug":"code-word-detection-in-fraud-investigations","title":"Code Word Detection in Fraud Investigations using a Deep-Learning Approach","date":"2021-03-17","arxiv_id":"2103.09606","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-images-for-analyzing-claims-in","slug":"on-the-role-of-images-for-analyzing-claims-in","title":"On the Role of Images for Analyzing Claims in Social Media","date":"2021-03-17","arxiv_id":"2103.09602","n_code_links":1,"syntology":null},{"paper":null,"slug":"sml-a-new-semantic-embedding-alignment","title":"SILT: Efficient transformer training for inter-lingual inference","date":"2021-03-17","arxiv_id":"2103.09635","n_code_links":0,"syntology":null},{"paper":"/paper/trans-svnet-accurate-phase-recognition-from","slug":"trans-svnet-accurate-phase-recognition-from","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","date":"2021-03-17","arxiv_id":"2103.09712","n_code_links":1,"syntology":null},{"paper":"/paper/uniparma-semeval-2021-task-5-toxic-spans","slug":"uniparma-semeval-2021-task-5-toxic-spans","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","date":"2021-03-17","arxiv_id":"2103.09645","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-look-one-level-feature","slug":"you-only-look-one-level-feature","title":"You Only Look One-level Feature","date":"2021-03-17","arxiv_id":"2103.09460","n_code_links":6,"syntology":null},{"paper":"/paper/dense-interaction-learning-for-video-based","slug":"dense-interaction-learning-for-video-based","title":"Dense Interaction Learning for Video-based Person Re-identification","date":"2021-03-16","arxiv_id":"2103.09013","n_code_links":0,"syntology":null},{"paper":null,"slug":"kgsynnet-a-novel-entity-synonyms-discovery","title":"KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph","date":"2021-03-16","arxiv_id":"2103.08893","n_code_links":0,"syntology":null},{"paper":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","n_code_links":2,"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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["intersun/LightningDOT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"robustly-optimized-and-distilled-training-for","title":"Robustly Optimized and Distilled Training for Natural Language Understanding","date":"2021-03-16","arxiv_id":"2103.08809","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-driven-description-synthesis-for","title":"Knowledge driven Description Synthesis for Floor Plan Interpretation","date":"2021-03-15","arxiv_id":"2103.08298","n_code_links":0,"syntology":null},{"paper":"/paper/improving-code-summarization-with-block-wise","slug":"improving-code-summarization-with-block-wise","title":"Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting","date":"2021-03-14","arxiv_id":"2103.07845","n_code_links":1,"syntology":null},{"paper":null,"slug":"semvlp-vision-language-pre-training-by-1","title":"SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels","date":"2021-03-14","arxiv_id":"2103.07829","n_code_links":0,"syntology":null},{"paper":"/paper/transfg-a-transformer-architecture-for-fine","slug":"transfg-a-transformer-architecture-for-fine","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","date":"2021-03-14","arxiv_id":"2103.07976","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TACJu/TransFG"],"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/approximating-how-single-head-attention","slug":"approximating-how-single-head-attention","title":"Approximating How Single Head Attention Learns","date":"2021-03-13","arxiv_id":"2103.07601","n_code_links":1,"syntology":null},{"paper":null,"slug":"embedding-calibration-for-music-semantic","title":"Optimal Embedding Calibration for Symbolic Music Similarity","date":"2021-03-13","arxiv_id":"2103.07656","n_code_links":0,"syntology":null},{"paper":null,"slug":"targeted-aspect-based-multimodal-sentiment","title":"Targeted aspect based multimodal sentiment analysis:an attention capsule extraction and multi-head fusion network","date":"2021-03-13","arxiv_id":"2103.07659","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-mining-of-stocktwits-data-for-predicting","title":"Text Mining of Stocktwits Data for Predicting Stock Prices","date":"2021-03-13","arxiv_id":"2103.16388","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-dictionary-based-language-model","title":"Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation","date":"2021-03-12","arxiv_id":"2103.07040","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-the-performance-of-nlp-toolkits-and","title":"Comparing the Performance of NLP Toolkits and Evaluation measures in Legal Tech","date":"2021-03-12","arxiv_id":"2103.11792","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-and-improving-bert-performance-on","title":"Explaining and Improving BERT Performance on Lexical Semantic Change Detection","date":"2021-03-12","arxiv_id":"2103.07259","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-bert-a-cross-disciplinary-knowledge","title":"Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability","date":"2021-03-12","arxiv_id":"2103.07162","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-architecture-search-based-on-cartesian","title":"Neural Architecture Search based on Cartesian Genetic Programming Coding Method","date":"2021-03-12","arxiv_id":"2103.07173","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-the-behavior-of-dealers-in-over","title":"Predicting the Behavior of Dealers in Over-The-Counter Corporate Bond Markets","date":"2021-03-12","arxiv_id":"2103.09098","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-random-network-for-fine-grained","title":"Sequential Random Network for Fine-grained Image Classification","date":"2021-03-12","arxiv_id":"2103.07230","n_code_links":0,"syntology":null},{"paper":null,"slug":"severity-quantification-and-lesion","title":"Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer","date":"2021-03-12","arxiv_id":"2103.07062","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-for-covid-19-cxr-diagnosis","title":"Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus","date":"2021-03-12","arxiv_id":"2103.07055","n_code_links":0,"syntology":null},{"paper":"/paper/canine-pre-training-an-efficient-tokenization","slug":"canine-pre-training-an-efficient-tokenization","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","date":"2021-03-11","arxiv_id":"2103.06874","n_code_links":6,"syntology":null},{"paper":null,"slug":"composite-re-ranking-for-efficient-document","title":"Composite Re-Ranking for Efficient Document Search with BERT","date":"2021-03-11","arxiv_id":"2103.06499","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-3d-multi-channel-sign-language","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","date":"2021-03-11","arxiv_id":"2103.06982","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-morphological-embeddings-for-1","title":"Evaluation of Morphological Embeddings for the Russian Language","date":"2021-03-11","arxiv_id":"2103.06628","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairfil-contrastive-neural-debiasing-method-1","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","date":"2021-03-11","arxiv_id":"2103.06413","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bi-encoder-document-ranking-models","slug":"improving-bi-encoder-document-ranking-models","title":"Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation","date":"2021-03-11","arxiv_id":"2103.06523","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightmbert-a-simple-yet-effective-method-for","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","date":"2021-03-11","arxiv_id":"2103.06418","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-improving-deep-learning-trace-analysis","title":"On Improving Deep Learning Trace Analysis with System Call Arguments","date":"2021-03-11","arxiv_id":"2103.06915","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-text-to-sql-learning-with","title":"Self-supervised Text-to-SQL Learning with Header Alignment Training","date":"2021-03-11","arxiv_id":"2103.06402","n_code_links":0,"syntology":null},{"paper":"/paper/towards-multi-sense-cross-lingual-alignment-1","slug":"towards-multi-sense-cross-lingual-alignment-1","title":"Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings","date":"2021-03-11","arxiv_id":"2103.06459","n_code_links":1,"syntology":null},{"paper":"/paper/unknown-object-segmentation-from-stereo","slug":"unknown-object-segmentation-from-stereo","title":"Unknown Object Segmentation from Stereo Images","date":"2021-03-11","arxiv_id":"2103.06796","n_code_links":2,"syntology":null},{"paper":"/paper/cuad-an-expert-annotated-nlp-dataset-for","slug":"cuad-an-expert-annotated-nlp-dataset-for","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","date":"2021-03-10","arxiv_id":"2103.06268","n_code_links":2,"syntology":null},{"paper":"/paper/hurdles-to-progress-in-long-form-question","slug":"hurdles-to-progress-in-long-form-question","title":"Hurdles to Progress in Long-form Question Answering","date":"2021-03-10","arxiv_id":"2103.06332","n_code_links":2,"syntology":null},{"paper":"/paper/majority-voting-with-bidirectional-pre","slug":"majority-voting-with-bidirectional-pre","title":"Majority Voting with Bidirectional Pre-translation For Bitext Retrieval","date":"2021-03-10","arxiv_id":"2103.06369","n_code_links":1,"syntology":null},{"paper":null,"slug":"ceqe-contextualized-embeddings-for-query","title":"CEQE: Contextualized Embeddings for Query Expansion","date":"2021-03-09","arxiv_id":"2103.05256","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-transformers-as-universal","slug":"pretrained-transformers-as-universal","title":"Pretrained Transformers as Universal Computation Engines","date":"2021-03-09","arxiv_id":"2103.05247","n_code_links":4,"syntology":null},{"paper":"/paper/language-models-have-a-moral-dimension","slug":"language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","arxiv_id":"2103.11790","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["ml-research/MoRT_NMI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify-1","title":"SKILLBERT: “SKILLING” THE BERT TO CLASSIFY SKILLS!","date":"2021-03-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mtlhealth-a-deep-learning-system-for","title":"MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays","date":"2021-03-07","arxiv_id":"2103.04290","n_code_links":0,"syntology":null},{"paper":null,"slug":"orthogonal-attention-a-cloze-style-approach","title":"Orthogonal Attention: A Cloze-Style Approach to Negation Scope Resolution","date":"2021-03-07","arxiv_id":"2103.04294","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":"/paper/transbts-multimodal-brain-tumor-segmentation","slug":"transbts-multimodal-brain-tumor-segmentation","title":"TransBTS: Multimodal Brain Tumor Segmentation Using Transformer","date":"2021-03-07","arxiv_id":"2103.04430","n_code_links":3,"syntology":null},{"paper":"/paper/investigating-on-incorporating-pretrained-and","slug":"investigating-on-incorporating-pretrained-and","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","date":"2021-03-06","arxiv_id":"2103.04088","n_code_links":1,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-pure-attention","slug":"attention-is-not-all-you-need-pure-attention","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","date":"2021-03-05","arxiv_id":"2103.03404","n_code_links":1,"syntology":null},{"paper":"/paper/dual-pointer-network-for-fast-extraction-of","slug":"dual-pointer-network-for-fast-extraction-of","title":"Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence","date":"2021-03-05","arxiv_id":"2103.03509","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-pretrained-multilingual-bert","title":"Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis","date":"2021-03-05","arxiv_id":"2103.03732","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-for-multilingual","title":"Hierarchical Transformer for Multilingual Machine Translation","date":"2021-03-05","arxiv_id":"2103.03589","n_code_links":0,"syntology":null},{"paper":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 3 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) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"malbert-using-transformers-for-cybersecurity","title":"MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection","date":"2021-03-05","arxiv_id":"2103.03806","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hendrycks/math"],"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","unlocated"]}}},{"paper":null,"slug":"non-invasive-self-attention-for-side","title":"Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation","date":"2021-03-05","arxiv_id":"2103.03578","n_code_links":0,"syntology":null}],"record_sha256":"2026efadecd1fe9f85b2ff7771ff63fbc302d9a779d79c81e9c56d9a3ea61dbb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}