{"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/209","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":209,"pages_in_order":249,"rows_per_page":100,"rows":[20801,20900],"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/208","next":"/method/multi-head-attention/papers/210","papers":[{"paper":null,"slug":"emotion-dynamics-modeling-via-bert","title":"Emotion Dynamics Modeling via BERT","date":"2021-04-15","arxiv_id":"2104.07252","n_code_links":0,"syntology":null},{"paper":"/paper/explagraphs-an-explanation-graph-generation","slug":"explagraphs-an-explanation-graph-generation","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","date":"2021-04-15","arxiv_id":"2104.07644","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["swarnaHub/ExplaGraphs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","n_code_links":4,"syntology":null},{"paper":"/paper/nt5-training-t5-to-perform-numerical","slug":"nt5-training-t5-to-perform-numerical","title":"NT5?! Training T5 to Perform Numerical Reasoning","date":"2021-04-15","arxiv_id":"2104.07307","n_code_links":1,"syntology":null},{"paper":"/paper/points-as-queries-weakly-semi-supervised","slug":"points-as-queries-weakly-semi-supervised","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","date":"2021-04-15","arxiv_id":"2104.07434","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":null}},{"paper":null,"slug":"privacy-adaptive-bert-for-natural-language","title":"Natural Language Understanding with Privacy-Preserving BERT","date":"2021-04-15","arxiv_id":"2104.07504","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-text-line-recognition-models","slug":"rethinking-text-line-recognition-models","title":"Rethinking Text Line Recognition Models","date":"2021-04-15","arxiv_id":"2104.07787","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-object-segmentation-by","slug":"self-supervised-video-object-segmentation-by","title":"Self-supervised Video Object Segmentation by Motion Grouping","date":"2021-04-15","arxiv_id":"2104.07658","n_code_links":0,"syntology":null},{"paper":"/paper/shoulder-implant-x-ray-manufacturer","slug":"shoulder-implant-x-ray-manufacturer","title":"Shoulder Implant X-Ray Manufacturer Classification: Exploring with Vision Transformer","date":"2021-04-15","arxiv_id":"2104.07667","n_code_links":1,"syntology":null},{"paper":null,"slug":"sina-bert-a-pre-trained-language-model-for","title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","date":"2021-04-15","arxiv_id":"2104.07613","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-aware-graph-to-graph-transformer-for","slug":"syntax-aware-graph-to-graph-transformer-for","title":"Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling","date":"2021-04-15","arxiv_id":"2104.07704","n_code_links":0,"syntology":null},{"paper":"/paper/text-guide-improving-the-quality-of-long-text","slug":"text-guide-improving-the-quality-of-long-text","title":"Text Guide: Improving the quality of long text classification by a text selection method based on feature importance","date":"2021-04-15","arxiv_id":"2104.07225","n_code_links":1,"syntology":null},{"paper":"/paper/torontocl-at-cmcl-2021-shared-task-roberta","slug":"torontocl-at-cmcl-2021-shared-task-roberta","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","date":"2021-04-15","arxiv_id":"2104.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"uhd-bert-bucketed-ultra-high-dimensional","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","date":"2021-04-15","arxiv_id":"2104.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"uit-e10dot3-at-semeval-2021-task-5-toxic","title":"UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches","date":"2021-04-15","arxiv_id":"2104.07376","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-using-low-level-chest-x","title":"Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification","date":"2021-04-15","arxiv_id":"2104.07235","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-interpretability-illusion-for-bert","title":"An Interpretability Illusion for BERT","date":"2021-04-14","arxiv_id":"2104.07143","n_code_links":0,"syntology":null},{"paper":"/paper/an-introduction-of-mini-alphastar","slug":"an-introduction-of-mini-alphastar","title":"An Introduction of mini-AlphaStar","date":"2021-04-14","arxiv_id":"2104.06890","n_code_links":1,"syntology":null},{"paper":"/paper/decoupled-spatial-temporal-transformer-for","slug":"decoupled-spatial-temporal-transformer-for","title":"Decoupled Spatial-Temporal Transformer for Video Inpainting","date":"2021-04-14","arxiv_id":"2104.06637","n_code_links":1,"syntology":null},{"paper":null,"slug":"demystifying-bert-implications-for","title":"Demystifying BERT: Implications for Accelerator Design","date":"2021-04-14","arxiv_id":"2104.08335","n_code_links":0,"syntology":null},{"paper":null,"slug":"dependency-parsing-based-semantic","title":"Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis","date":"2021-04-14","arxiv_id":"2104.06835","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-representations-of-text-by-1","title":"Disentangling Representations of Text by Masking Transformers","date":"2021-04-14","arxiv_id":"2104.07155","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-driven-answer-generation-for","title":"Knowledge-driven Answer Generation for Conversational Search","date":"2021-04-14","arxiv_id":"2104.06892","n_code_links":0,"syntology":null},{"paper":"/paper/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":null,"slug":"non-autoregressive-sequence-to-sequence-voice","title":"Non-autoregressive sequence-to-sequence voice conversion","date":"2021-04-14","arxiv_id":"2104.06793","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-robustness-of-goal-oriented-dialogue","slug":"on-the-robustness-of-goal-oriented-dialogue","title":"On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise","date":"2021-04-14","arxiv_id":"2104.07149","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-attention-with-linear-units","slug":"sparse-attention-with-linear-units","title":"Sparse Attention with Linear Units","date":"2021-04-14","arxiv_id":"2104.07012","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["bzhangGo/zero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"paper":"/paper/static-embeddings-as-efficient-knowledge","slug":"static-embeddings-as-efficient-knowledge","title":"Static Embeddings as Efficient Knowledge Bases?","date":"2021-04-14","arxiv_id":"2104.07094","n_code_links":1,"syntology":null},{"paper":"/paper/tweac-transformer-with-extendable-qa-agent","slug":"tweac-transformer-with-extendable-qa-agent","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","date":"2021-04-14","arxiv_id":"2104.07081","n_code_links":1,"syntology":null},{"paper":"/paper/vtgan-semi-supervised-retinal-image-synthesis","slug":"vtgan-semi-supervised-retinal-image-synthesis","title":"VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers","date":"2021-04-14","arxiv_id":"2104.06757","n_code_links":2,"syntology":null},{"paper":"/paper/1-bit-lamb-communication-efficient-large","slug":"1-bit-lamb-communication-efficient-large","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","date":"2021-04-13","arxiv_id":"2104.06069","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-a-transformer-pass-the-wug-test-tuning","title":"Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models","date":"2021-04-13","arxiv_id":"2104.06483","n_code_links":0,"syntology":null},{"paper":"/paper/discourse-probing-of-pretrained-language","slug":"discourse-probing-of-pretrained-language","title":"Discourse Probing of Pretrained Language Models","date":"2021-04-13","arxiv_id":"2104.05882","n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-contextualised-language-modelling","slug":"large-scale-contextualised-language-modelling","title":"Large-Scale Contextualised Language Modelling for Norwegian","date":"2021-04-13","arxiv_id":"2104.06546","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ltgoslo/NorBERT","ltgoslo/norec_sentence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mediators-in-determining-what-processing-bert","slug":"mediators-in-determining-what-processing-bert","title":"Mediators in Determining what Processing BERT Performs First","date":"2021-04-13","arxiv_id":"2104.06400","n_code_links":1,"syntology":null},{"paper":"/paper/ms2-multi-document-summarization-of-medical","slug":"ms2-multi-document-summarization-of-medical","title":"MS2: Multi-Document Summarization of Medical Studies","date":"2021-04-13","arxiv_id":"2104.06486","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allenai/ms2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","n_code_links":6,"syntology":{"ran":8,"of":25,"n_ran_checked":8,"n_instrument":0,"unverified":17,"pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 17 unverified","official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semantic-maps-and-metrics-for-science","title":"Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders","date":"2021-04-13","arxiv_id":"2104.05928","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-methods-for-recognizing","title":"Transformer-based Methods for Recognizing Ultra Fine-grained Entities (RUFES)","date":"2021-04-13","arxiv_id":"2104.06048","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2021-task-7-adversarial-multi","title":"UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense","date":"2021-04-13","arxiv_id":"2104.06063","n_code_links":0,"syntology":null},{"paper":"/paper/vit-v-net-vision-transformer-for-unsupervised","slug":"vit-v-net-vision-transformer-for-unsupervised","title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","date":"2021-04-13","arxiv_id":"2104.06468","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["junyuchen245/ViT-V-Net_for_3D_Image_Registration_Pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-based-freedom-to-operate-patent-analysis","title":"BERT based freedom to operate patent analysis","date":"2021-04-12","arxiv_id":"2105.00817","n_code_links":0,"syntology":null},{"paper":"/paper/cloth-interactive-transformer-for-virtual-try","slug":"cloth-interactive-transformer-for-virtual-try","title":"Cloth Interactive Transformer for Virtual Try-On","date":"2021-04-12","arxiv_id":"2104.05519","n_code_links":1,"syntology":null},{"paper":"/paper/escaping-the-big-data-paradigm-with-compact","slug":"escaping-the-big-data-paradigm-with-compact","title":"Escaping the Big Data Paradigm with Compact Transformers","date":"2021-04-12","arxiv_id":"2104.05704","n_code_links":9,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["SHI-Labs/Compact-Transformers"],"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":"family-of-origin-and-family-of-choice","title":"Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation","date":"2021-04-12","arxiv_id":"2104.05848","n_code_links":0,"syntology":null},{"paper":"/paper/fighting-the-covid-19-infodemic-with-a","slug":"fighting-the-covid-19-infodemic-with-a","title":"Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble","date":"2021-04-12","arxiv_id":"2104.05745","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-transformers-for-identifying-self","slug":"fine-tuning-transformers-for-identifying-self","title":"Fine-Tuning Transformers for Identifying Self-Reporting Potential Cases and Symptoms of COVID-19 in Tweets","date":"2021-04-12","arxiv_id":"2104.05501","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-dynamic-and-hierarchical-traffic","title":"Learning dynamic and hierarchical traffic spatiotemporal features with Transformer","date":"2021-04-12","arxiv_id":"2104.05163","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-remove-towards-isotropic-pre","slug":"learning-to-remove-towards-isotropic-pre","title":"Learning to Remove: Towards Isotropic Pre-trained BERT Embedding","date":"2021-04-12","arxiv_id":"2104.05274","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-synthesize-data-for-semantic","slug":"learning-to-synthesize-data-for-semantic","title":"Learning to Synthesize Data for Semantic Parsing","date":"2021-04-12","arxiv_id":"2104.05827","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-language-models-predict-human","slug":"multilingual-language-models-predict-human","title":"Multilingual Language Models Predict Human Reading Behavior","date":"2021-04-12","arxiv_id":"2104.05433","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-representation-learning-for-scientific","title":"On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs","date":"2021-04-12","arxiv_id":"2104.05866","n_code_links":0,"syntology":null},{"paper":"/paper/paragraph-level-simplification-of-medical","slug":"paragraph-level-simplification-of-medical","title":"Paragraph-level Simplification of Medical Texts","date":"2021-04-12","arxiv_id":"2104.05767","n_code_links":1,"syntology":null},{"paper":null,"slug":"updater-extractor-architecture-for-inductive","title":"Updater-Extractor Architecture for Inductive World State Representations","date":"2021-04-12","arxiv_id":"2104.05500","n_code_links":0,"syntology":null},{"paper":"/paper/whose-heritage-classification-of-unesco-world","slug":"whose-heritage-classification-of-unesco-world","title":"WHOSe Heritage: Classification of UNESCO World Heritage \"Outstanding Universal Value\" Documents with Soft Labels","date":"2021-04-12","arxiv_id":"2104.05547","n_code_links":1,"syntology":null},{"paper":"/paper/does-syntax-matter-a-strong-baseline-for","slug":"does-syntax-matter-a-strong-baseline-for","title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","date":"2021-04-11","arxiv_id":"2104.04986","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-encoders-for-improved-monolingual","slug":"fine-tuning-encoders-for-improved-monolingual","title":"Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling","date":"2021-04-11","arxiv_id":"2104.05064","n_code_links":1,"syntology":null},{"paper":null,"slug":"innovative-bert-based-reranking-language","title":"Innovative Bert-based Reranking Language Models for Speech Recognition","date":"2021-04-11","arxiv_id":"2104.04950","n_code_links":0,"syntology":null},{"paper":"/paper/unidrop-a-simple-yet-effective-technique-to","slug":"unidrop-a-simple-yet-effective-technique-to","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","date":"2021-04-11","arxiv_id":"2104.04946","n_code_links":0,"syntology":null},{"paper":"/paper/meta-tuning-language-models-to-answer-prompts","slug":"meta-tuning-language-models-to-answer-prompts","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","date":"2021-04-10","arxiv_id":"2104.04670","n_code_links":1,"syntology":null},{"paper":"/paper/mipt-nsu-utmn-at-semeval-2021-task-5","slug":"mipt-nsu-utmn-at-semeval-2021-task-5","title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","date":"2021-04-10","arxiv_id":"2104.04739","n_code_links":1,"syntology":null},{"paper":null,"slug":"non-autoregressive-transformer-based-end-to","title":"Non-autoregressive Transformer-based End-to-end ASR using BERT","date":"2021-04-10","arxiv_id":"2104.04805","n_code_links":0,"syntology":null},{"paper":"/paper/zs-bert-towards-zero-shot-relation-extraction","slug":"zs-bert-towards-zero-shot-relation-extraction","title":"ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning","date":"2021-04-10","arxiv_id":"2104.04697","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-transformer-networks-for-time-series","title":"Deep Transformer Networks for Time Series Classification: The NPP Safety Case","date":"2021-04-09","arxiv_id":"2104.05448","n_code_links":0,"syntology":null},{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":"/paper/know-what-and-know-where-an-object-and-room","slug":"know-what-and-know-where-an-object-and-room","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","date":"2021-04-09","arxiv_id":"2104.04167","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":"/paper/text2chart-a-multi-staged-chart-generator","slug":"text2chart-a-multi-staged-chart-generator","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","date":"2021-04-09","arxiv_id":"2104.04584","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-the-end-of-history-for-nlp","title":"Transformers: \"The End of History\" for NLP?","date":"2021-04-09","arxiv_id":"2105.00813","n_code_links":0,"syntology":null},{"paper":null,"slug":"layer-reduction-accelerating-conformer-based","title":"Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency","date":"2021-04-08","arxiv_id":"2105.00812","n_code_links":0,"syntology":null},{"paper":"/paper/lone-pine-at-semeval-2021-task-5-fine-grained","slug":"lone-pine-at-semeval-2021-task-5-fine-grained","title":"Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic","date":"2021-04-08","arxiv_id":"2104.03506","n_code_links":1,"syntology":null},{"paper":"/paper/probing-bert-in-hyperbolic-spaces-1","slug":"probing-bert-in-hyperbolic-spaces-1","title":"Probing BERT in Hyperbolic Spaces","date":"2021-04-08","arxiv_id":"2104.03869","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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":["FranxYao/PoincareProbe"],"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":"/paper/revisiting-simple-neural-probabilistic","slug":"revisiting-simple-neural-probabilistic","title":"Revisiting Simple Neural Probabilistic Language Models","date":"2021-04-08","arxiv_id":"2104.03474","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["SimengSun/revisit-nplm"],"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":"uppsala-nlp-at-semeval-2021-task-2","title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation","date":"2021-04-08","arxiv_id":"2104.03767","n_code_links":0,"syntology":null},{"paper":"/paper/better-neural-machine-translation-by","slug":"better-neural-machine-translation-by","title":"Better Neural Machine Translation by Extracting Linguistic Information from BERT","date":"2021-04-07","arxiv_id":"2104.02831","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-pre-trained-word-embeddings-and","title":"Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identification","date":"2021-04-07","arxiv_id":"2104.03285","n_code_links":0,"syntology":null},{"paper":"/paper/everything-s-talkin-pareidolia-face","slug":"everything-s-talkin-pareidolia-face","title":"Everything's Talkin': Pareidolia Face Reenactment","date":"2021-04-07","arxiv_id":"2104.03061","n_code_links":1,"syntology":null},{"paper":null,"slug":"facial-attribute-transformers-for-precise-and","title":"Facial Attribute Transformers for Precise and Robust Makeup Transfer","date":"2021-04-07","arxiv_id":"2104.02894","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-a-pre-trained-model-is-a-key-for","title":"Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0","date":"2021-04-07","arxiv_id":"2104.02851","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-verbal-metaphors-by-paraphrasing","title":"Interpreting Verbal Metaphors by Paraphrasing","date":"2021-04-07","arxiv_id":"2104.03391","n_code_links":0,"syntology":null},{"paper":null,"slug":"li-net-large-pose-identity-preserving-face","title":"LI-Net: Large-Pose Identity-Preserving Face Reenactment Network","date":"2021-04-07","arxiv_id":"2104.02850","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-out-of-the-box-end-to-end-pre-training","slug":"seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","n_code_links":3,"syntology":null},{"paper":"/paper/speak-or-chat-with-me-end-to-end-spoken","slug":"speak-or-chat-with-me-end-to-end-spoken","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","date":"2021-04-07","arxiv_id":"2104.05752","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-evaluation-of-word-embedding","slug":"an-empirical-evaluation-of-word-embedding","title":"An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks","date":"2021-04-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-head-masking-for-inference-time","title":"Attention Head Masking for Inference Time Content Selection in Abstractive Summarization","date":"2021-04-06","arxiv_id":"2104.02205","n_code_links":0,"syntology":null},{"paper":"/paper/codetrans-towards-cracking-the-language-of","slug":"codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-transfer-learning-for-nlp-with","slug":"efficient-transfer-learning-for-nlp-with","title":"Efficient transfer learning for NLP with ELECTRA","date":"2021-04-06","arxiv_id":"2104.02756","n_code_links":1,"syntology":null},{"paper":"/paper/fourier-image-transformer","slug":"fourier-image-transformer","title":"Fourier Image Transformer","date":"2021-04-06","arxiv_id":"2104.02555","n_code_links":1,"syntology":null},{"paper":"/paper/hbert-biascorp-fighting-racism-on-the-web","slug":"hbert-biascorp-fighting-racism-on-the-web","title":"HBert + BiasCorp -- Fighting Racism on the Web","date":"2021-04-06","arxiv_id":"2104.02242","n_code_links":0,"syntology":null},{"paper":"/paper/lt-lm-a-novel-non-autoregressive-language","slug":"lt-lm-a-novel-non-autoregressive-language","title":"LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring","date":"2021-04-06","arxiv_id":"2104.02526","n_code_links":1,"syntology":null},{"paper":null,"slug":"muslcat-multi-scale-multi-level-convolutional","title":"MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms","date":"2021-04-06","arxiv_id":"2104.02309","n_code_links":0,"syntology":null},{"paper":null,"slug":"ode-transformer-an-ordinary-differential","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation","date":"2021-04-06","arxiv_id":"2104.02308","n_code_links":0,"syntology":null},{"paper":"/paper/variable-selection-with-missing-data-in-both","slug":"variable-selection-with-missing-data-in-both","title":"Variable selection with missing data in both covariates and outcomes: Imputation and machine learning","date":"2021-04-06","arxiv_id":"2104.02769","n_code_links":1,"syntology":null},{"paper":null,"slug":"variational-transformer-networks-for-layout","title":"Variational Transformer Networks for Layout Generation","date":"2021-04-06","arxiv_id":"2104.02416","n_code_links":0,"syntology":null},{"paper":"/paper/ast-audio-spectrogram-transformer","slug":"ast-audio-spectrogram-transformer","title":"AST: Audio Spectrogram Transformer","date":"2021-04-05","arxiv_id":"2104.01778","n_code_links":5,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["YuanGongND/ast"],"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":"covid-19-sentiment-analysis-via-deep-learning","title":"COVID-19 sentiment analysis via deep learning during the rise of novel cases","date":"2021-04-05","arxiv_id":"2104.10662","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-transformers-in-emotion-recognition","title":"Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA","date":"2021-04-05","arxiv_id":"2104.02041","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-distance-a-new-metric-for-asr","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","date":"2021-04-05","arxiv_id":"2104.02138","n_code_links":0,"syntology":null},{"paper":"/paper/what-s-the-best-place-for-an-ai-conference","slug":"what-s-the-best-place-for-an-ai-conference","title":"What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult","date":"2021-04-05","arxiv_id":"2104.01940","n_code_links":0,"syntology":null}],"record_sha256":"07fd23ec259ceb44e186060000f0786a2fd019c92760d570094e815c02bdcaa0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}