{"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/attention/papers/272","list_of":"/method/attention","method":"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":272,"pages_in_order":316,"rows_per_page":100,"rows":[27101,27200],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/271","next":"/method/attention/papers/273","papers":[{"paper":null,"slug":"dreca-a-general-task-augmentation-strategy","title":"DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-objective-fine-tuning-of-bert-for-entity","slug":"dual-objective-fine-tuning-of-bert-for-entity","title":"Dual-Objective Fine-Tuning of BERT for Entity Matching","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/efficiently-summarizing-text-and-graph","slug":"efficiently-summarizing-text-and-graph","title":"Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emotion-infused-models-for-explainable","slug":"emotion-infused-models-for-explainable","title":"Emotion-Infused Models for Explainable Psychological Stress Detection","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-multihop-retrieval-for","slug":"end-to-end-multihop-retrieval-for","title":"Iterative Hierarchical Attention for Answering Complex Questions over Long Documents","date":"2021-06-01","arxiv_id":"2106.00200","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-perdetry-test-generating-new-meanings-for","title":"GPT Perdetry Test: Generating new meanings for new words","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hie-bart-document-summarization-with","slug":"hie-bart-document-summarization-with","title":"Hie-BART: Document Summarization with Hierarchical BART","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/honest-measuring-hurtful-sentence-completion","slug":"honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/icompass-at-nlp4if-2021-fighting-the-covid-19","slug":"icompass-at-nlp4if-2021-fighting-the-covid-19","title":"iCompass at NLP4IF-2021–Fighting the COVID-19 Infodemic","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/implicit-representations-of-meaning-in-neural","slug":"implicit-representations-of-meaning-in-neural","title":"Implicit Representations of Meaning in Neural Language Models","date":"2021-06-01","arxiv_id":"2106.00737","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-automatic-hate-speech-detection","title":"Improving Automatic Hate Speech Detection with Multiword Expression Features","date":"2021-06-01","arxiv_id":"2106.00237","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-grained-knowledge-distillation-for","title":"Multi-Grained Knowledge Distillation for Named Entity Recognition","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-hop-transformer-for-document-level","title":"Multi-Hop Transformer for Document-Level Machine Translation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"negation-typology-and-general-representation","title":"Negation typology and general representation models for cross-lingual zero-shot negation scope resolution in Russian, French, and Spanish.","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-using-distributed-representations-of","slug":"on-using-distributed-representations-of","title":"On using distributed representations of source code for the detection of C security vulnerabilities","date":"2021-06-01","arxiv_id":"2106.01367","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-vehicles-trajectories-in-urban","title":"Predicting Vehicles Trajectories in Urban Scenarios with Transformer Networks and Augmented Information","date":"2021-06-01","arxiv_id":"2106.00559","n_code_links":0,"syntology":null},{"paper":null,"slug":"quadrupletbert-an-efficient-model-for","title":"QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"script-self-critic-pretraining-of","title":"SCRIPT: Self-Critic PreTraining of Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shuffled-token-detection-for-refining-pre","title":"Shuffled-token Detection for Refining Pre-trained RoBERTa","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/supervised-neural-clustering-via-latent","slug":"supervised-neural-clustering-via-latent","title":"Supervised Neural Clustering via Latent Structured Output Learning: Application to Question Intents","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"thg-transformer-with-hyperbolic-geometry","title":"THG: Transformer with Hyperbolic Geometry","date":"2021-06-01","arxiv_id":"2106.07350","n_code_links":0,"syntology":null},{"paper":"/paper/too-much-in-common-shifting-of-embeddings-in","slug":"too-much-in-common-shifting-of-embeddings-in","title":"Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-a-comprehensive-understanding-and","title":"Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-modeling-the-style-of-translators-in","title":"Towards Modeling the Style of Translators in Neural Machine Translation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-language-models-under-resource","title":"Training Language Models under Resource Constraints for Adversarial Advertisement Detection","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transvos-video-object-segmentation-with","slug":"transvos-video-object-segmentation-with","title":"TransVOS: Video Object Segmentation with Transformers","date":"2021-06-01","arxiv_id":"2106.00588","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-integrated-gradients-to-explain","title":"Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT","date":"2021-06-01","arxiv_id":"2106.07349","n_code_links":0,"syntology":null},{"paper":null,"slug":"wikitalkedit-a-dataset-for-modeling-editors","title":"WikiTalkEdit: A Dataset for modeling Editors' behaviors on Wikipedia","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/you-only-look-at-one-sequence-rethinking","slug":"you-only-look-at-one-sequence-rethinking","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","date":"2021-06-01","arxiv_id":"2106.00666","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":2,"n_instrument":3,"unverified":5,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hustvl/YOLOS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/analogous-to-evolutionary-algorithm-designing","slug":"analogous-to-evolutionary-algorithm-designing","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","date":"2021-05-31","arxiv_id":"2105.15089","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-noise-mitigating-the-impact-of-fine","slug":"beyond-noise-mitigating-the-impact-of-fine","title":"Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation","date":"2021-05-31","arxiv_id":"2105.15087","n_code_links":2,"syntology":null},{"paper":"/paper/cascaded-head-colliding-attention","slug":"cascaded-head-colliding-attention","title":"Cascaded Head-colliding Attention","date":"2021-05-31","arxiv_id":"2105.14850","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":5,"n_instrument":4,"unverified":1,"pointer_only":5,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LZhengisme/CODA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"paper":"/paper/choose-a-transformer-fourier-or-galerkin","slug":"choose-a-transformer-fourier-or-galerkin","title":"Choose a Transformer: Fourier or Galerkin","date":"2021-05-31","arxiv_id":"2105.14995","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["scaomath/galerkin-transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"exploring-sparse-expert-models-and-beyond","title":"M6-T: Exploring Sparse Expert Models and Beyond","date":"2021-05-31","arxiv_id":"2105.15082","n_code_links":0,"syntology":null},{"paper":"/paper/g-transformer-for-document-level-machine","slug":"g-transformer-for-document-level-machine","title":"G-Transformer for Document-level Machine Translation","date":"2021-05-31","arxiv_id":"2105.14761","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 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":["baoguangsheng/g-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-transfer-learning-impacts-linguistic","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","date":"2021-05-31","arxiv_id":"2105.15179","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-images-are-worth-16x16-words-dynamic","slug":"not-all-images-are-worth-16x16-words-dynamic","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","date":"2021-05-31","arxiv_id":"2105.15075","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["blackfeather-wang/Dynamic-Vision-Transformer","blackfeather-wang/dynamic-vision-transformer-mindspore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/segformer-simple-and-efficient-design-for","slug":"segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","arxiv_id":"2105.15203","n_code_links":28,"syntology":{"ran":66,"of":86,"n_ran_checked":62,"n_instrument":4,"unverified":20,"pointer_only":20,"phrase":"66 ran (of which 22 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 4 where Syntology's instrument failed) · 20 unverified","official":{"repos":["NVlabs/SegFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed","unlocated"]}}},{"paper":null,"slug":"training-electra-augmented-with-multi-word","title":"Training ELECTRA Augmented with Multi-word Selection","date":"2021-05-31","arxiv_id":"2106.00139","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-fact-verification-by-claim","slug":"zero-shot-fact-verification-by-claim","title":"Zero-shot Fact Verification by Claim Generation","date":"2021-05-31","arxiv_id":"2105.14682","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["teacherpeterpan/Zero-shot-Fact-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"a-compression-compilation-framework-for-on","title":"A Compression-Compilation Framework for On-mobile Real-time BERT Applications","date":"2021-05-30","arxiv_id":"2106.00526","n_code_links":0,"syntology":null},{"paper":"/paper/gaze-estimation-using-transformer","slug":"gaze-estimation-using-transformer","title":"Gaze Estimation using Transformer","date":"2021-05-30","arxiv_id":"2105.14424","n_code_links":1,"syntology":null},{"paper":"/paper/human-interpretable-ai-enhancing-tsetlin","slug":"human-interpretable-ai-enhancing-tsetlin","title":"Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine","date":"2021-05-30","arxiv_id":"2105.14506","n_code_links":7,"syntology":null},{"paper":"/paper/lrtuner-a-learning-rate-tuner-for-deep-neural","slug":"lrtuner-a-learning-rate-tuner-for-deep-neural","title":"LRTuner: A Learning Rate Tuner for Deep Neural Networks","date":"2021-05-30","arxiv_id":"2105.14526","n_code_links":2,"syntology":null},{"paper":"/paper/mlpruning-a-multilevel-structured-pruning","slug":"mlpruning-a-multilevel-structured-pruning","title":"LEAP: Learnable Pruning for Transformer-based Models","date":"2021-05-30","arxiv_id":"2105.14636","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yaozhewei/mlpruning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nas-bert-task-agnostic-and-adaptive-size-bert","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","date":"2021-05-30","arxiv_id":"2105.14444","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-models-for-offensive-language","title":"Neural Models for Offensive Language Detection","date":"2021-05-30","arxiv_id":"2106.14609","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-deep-image-matching-for","slug":"transformer-based-deep-image-matching-for","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","date":"2021-05-30","arxiv_id":"2105.14432","n_code_links":2,"syntology":{"ran":13,"of":21,"n_ran_checked":9,"n_instrument":4,"unverified":8,"pointer_only":1,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["shengcailiao/QAConv","ShengcaiLiao/TransMatcher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"paper":"/paper/unsupervised-joint-learning-of-depth-optical","slug":"unsupervised-joint-learning-of-depth-optical","title":"Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video","date":"2021-05-30","arxiv_id":"2105.14520","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simple-voting-mechanism-for-online-sexist","title":"A Simple Voting Mechanism for Online Sexist Content Identification","date":"2021-05-29","arxiv_id":"2105.14309","n_code_links":0,"syntology":null},{"paper":"/paper/constructing-flow-graphs-from-procedural","slug":"constructing-flow-graphs-from-procedural","title":"Constructing Flow Graphs from Procedural Cybersecurity Texts","date":"2021-05-29","arxiv_id":"2105.14357","n_code_links":1,"syntology":null},{"paper":null,"slug":"foveater-foveated-transformer-for-image","title":"FoveaTer: Foveated Transformer for Image Classification","date":"2021-05-29","arxiv_id":"2105.14173","n_code_links":0,"syntology":null},{"paper":"/paper/korean-english-machine-translation-with","slug":"korean-english-machine-translation-with","title":"Korean-English Machine Translation with Multiple Tokenization Strategy","date":"2021-05-29","arxiv_id":"2105.14274","n_code_links":1,"syntology":null},{"paper":"/paper/less-is-more-pay-less-attention-in-vision","slug":"less-is-more-pay-less-attention-in-vision","title":"Less is More: Pay Less Attention in Vision Transformers","date":"2021-05-29","arxiv_id":"2105.14217","n_code_links":2,"syntology":null},{"paper":"/paper/sentiment-analysis-in-tweets-an-assessment","slug":"sentiment-analysis-in-tweets-an-assessment","title":"Sentiment analysis in tweets: an assessment study from classical to modern text representation models","date":"2021-05-29","arxiv_id":"2105.14373","n_code_links":1,"syntology":null},{"paper":null,"slug":"ufc-bert-unifying-multi-modal-controls-for","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","date":"2021-05-29","arxiv_id":"2105.14211","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-bert-inference-for-sequence","slug":"accelerating-bert-inference-for-sequence","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","date":"2021-05-28","arxiv_id":"2105.13878","n_code_links":1,"syntology":null},{"paper":"/paper/an-attention-free-transformer-1","slug":"an-attention-free-transformer-1","title":"An Attention Free Transformer","date":"2021-05-28","arxiv_id":"2105.14103","n_code_links":11,"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":null}},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","n_code_links":5,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/compositionally-restricted-attention-based","slug":"compositionally-restricted-attention-based","title":"Compositionally restricted attention-based network for materials property predictions","date":"2021-05-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-adaptive-pretraining-methods-for","title":"Domain-Adaptive Pretraining Methods for Dialogue Understanding","date":"2021-05-28","arxiv_id":"2105.13665","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-transformer-encoders-for","slug":"hierarchical-transformer-encoders-for","title":"Hierarchical Transformer Encoders for Vietnamese Spelling Correction","date":"2021-05-28","arxiv_id":"2105.13578","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-inheritance-for-pre-trained","slug":"knowledge-inheritance-for-pre-trained","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-05-28","arxiv_id":"2105.13880","n_code_links":2,"syntology":null},{"paper":"/paper/kvt-k-nn-attention-for-boosting-vision","slug":"kvt-k-nn-attention-for-boosting-vision","title":"KVT: k-NN Attention for Boosting Vision Transformers","date":"2021-05-28","arxiv_id":"2106.00515","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["damo-cv/kvt"],"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":["official"]}}},{"paper":"/paper/ptnet-a-high-resolution-infant-mri","slug":"ptnet-a-high-resolution-infant-mri","title":"PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer","date":"2021-05-28","arxiv_id":"2105.13993","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-on-line-sequence","title":"Reinforcement Learning for on-line Sequence Transformation","date":"2021-05-28","arxiv_id":"2105.14097","n_code_links":0,"syntology":null},{"paper":"/paper/rest-an-efficient-transformer-for-visual","slug":"rest-an-efficient-transformer-for-visual","title":"ResT: An Efficient Transformer for Visual Recognition","date":"2021-05-28","arxiv_id":"2105.13677","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 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) · 0 unverified","official":{"repos":["wofmanaf/ResT"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-mental-time-travel-a-hierarchical","slug":"towards-mental-time-travel-a-hierarchical","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","date":"2021-05-28","arxiv_id":"2105.14039","n_code_links":5,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 2 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) · 3 unverified","official":{"repos":["deepmind/deepmind-research","deepmind/dm_fast_mapping"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transcamp-graph-transformer-for-6-dof-camera","title":"TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation","date":"2021-05-28","arxiv_id":"2105.14065","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-source-free-domain","slug":"transformer-based-source-free-domain","title":"Transformer-Based Source-Free Domain Adaptation","date":"2021-05-28","arxiv_id":"2105.14138","n_code_links":1,"syntology":null},{"paper":"/paper/weighted-training-for-cross-task-learning","slug":"weighted-training-for-cross-task-learning","title":"Weighted Training for Cross-Task Learning","date":"2021-05-28","arxiv_id":"2105.14095","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["HornHehhf/TAWT"],"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":"contrastive-fine-tuning-improves-robustness","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","date":"2021-05-27","arxiv_id":"2105.12932","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosing-transformers-in-task-oriented","title":"Diagnosing Transformers in Task-Oriented Semantic Parsing","date":"2021-05-27","arxiv_id":"2105.13496","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-for","title":"Generative Adversarial Imitation Learning for Empathy-based AI","date":"2021-05-27","arxiv_id":"2105.13328","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-distilled-data-complexity-impact-the","title":"How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?","date":"2021-05-27","arxiv_id":"2105.12900","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dynamic-graph-representation-of","slug":"learning-dynamic-graph-representation-of","title":"Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention","date":"2021-05-27","arxiv_id":"2105.13495","n_code_links":2,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":15,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["egyptdj/stagin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"leveraging-linguistic-coordination-in","title":"Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT","date":"2021-05-27","arxiv_id":"2105.13479","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixqa-embedding-and-answer-mixing-for","title":"MixQA: Embedding and Answer Mixing for Question Answering","date":"2021-05-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"path-based-knowledge-reasoning-with-textual","title":"Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion","date":"2021-05-27","arxiv_id":"2105.13074","n_code_links":0,"syntology":null},{"paper":"/paper/raw-c-relatedness-of-ambiguous-words-in","slug":"raw-c-relatedness-of-ambiguous-words-in","title":"RAW-C: Relatedness of Ambiguous Words--in Context (A New Lexical Resource for English)","date":"2021-05-27","arxiv_id":"2105.13266","n_code_links":1,"syntology":null},{"paper":"/paper/selective-knowledge-distillation-for-neural","slug":"selective-knowledge-distillation-for-neural","title":"Selective Knowledge Distillation for Neural Machine Translation","date":"2021-05-27","arxiv_id":"2105.12967","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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":["LeslieOverfitting/selective_distillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"verb-sense-clustering-using-contextualized","title":"Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction","date":"2021-05-27","arxiv_id":"2105.13465","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-full-stack-accelerator-search-technique-for","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","date":"2021-05-26","arxiv_id":"2105.12842","n_code_links":0,"syntology":null},{"paper":"/paper/aggregating-nested-transformers","slug":"aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","arxiv_id":"2105.12723","n_code_links":6,"syntology":{"ran":19,"of":26,"n_ran_checked":18,"n_instrument":1,"unverified":7,"pointer_only":6,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 1 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["google-research/nested-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","n_code_links":2,"syntology":{"ran":10,"of":20,"n_ran_checked":10,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/bilingual-mutual-information-based-adaptive","slug":"bilingual-mutual-information-based-adaptive","title":"Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","date":"2021-05-26","arxiv_id":"2105.12523","n_code_links":1,"syntology":null},{"paper":null,"slug":"bionavi-np-biosynthesis-navigator-for-natural","title":"BioNavi-NP: Biosynthesis Navigator for Natural Products","date":"2021-05-26","arxiv_id":"2105.13121","n_code_links":0,"syntology":null},{"paper":"/paper/cogview-mastering-text-to-image-generation","slug":"cogview-mastering-text-to-image-generation","title":"CogView: Mastering Text-to-Image Generation via Transformers","date":"2021-05-26","arxiv_id":"2105.13290","n_code_links":4,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["THUDM/CogView"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deception-detection-in-text-and-its-relation","title":"Deception detection in text and its relation to the cultural dimension of individualism/collectivism","date":"2021-05-26","arxiv_id":"2105.12530","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-parallelism-making-4d-parallelism","title":"Sequence Parallelism: Long Sequence Training from System Perspective","date":"2021-05-26","arxiv_id":"2105.13120","n_code_links":0,"syntology":null},{"paper":"/paper/trade-the-event-corporate-events-detection","slug":"trade-the-event-corporate-events-detection","title":"Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading","date":"2021-05-26","arxiv_id":"2105.12825","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Zhihan1996/TradeTheEvent"],"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":null,"slug":"zero-shot-medical-entity-retrieval-without","title":"Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics","date":"2021-05-26","arxiv_id":"2105.12682","n_code_links":0,"syntology":null},{"paper":"/paper/consert-a-contrastive-framework-for-self","slug":"consert-a-contrastive-framework-for-self","title":"ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer","date":"2021-05-25","arxiv_id":"2105.11741","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-sensitive-visualization-of-deep","title":"Context-Sensitive Visualization of Deep Learning Natural Language Processing Models","date":"2021-05-25","arxiv_id":"2105.12202","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-multimodal-model-performance-with","slug":"enhance-multimodal-model-performance-with","title":"Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution","date":"2021-05-25","arxiv_id":"2105.13132","n_code_links":1,"syntology":null},{"paper":null,"slug":"extending-the-abstraction-of-personality","title":"Extending the Abstraction of Personality Types based on MBTI with Machine Learning and Natural Language Processing","date":"2021-05-25","arxiv_id":"2105.11798","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-of-generation-and","title":"Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation","date":"2021-05-25","arxiv_id":"2105.11696","n_code_links":0,"syntology":null},{"paper":null,"slug":"nukelm-pre-trained-and-fine-tuned-language","title":"NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains","date":"2021-05-25","arxiv_id":"2105.12192","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-transformer-for-explainable","slug":"personalized-transformer-for-explainable","title":"Personalized Transformer for Explainable Recommendation","date":"2021-05-25","arxiv_id":"2105.11601","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lileipisces/PETER"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"7c983163c7e9a17cc4777923e5475b69aff67e9b4b60440ccdaece0798b6dc91","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}