{"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/267","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":267,"pages_in_order":316,"rows_per_page":100,"rows":[26601,26700],"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/266","next":"/method/attention/papers/268","papers":[{"paper":null,"slug":"synchronous-syntactic-attention-for","title":"Synchronous Syntactic Attention for Transformer Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/taming-pre-trained-language-models-with-n","slug":"taming-pre-trained-language-models-with-n","title":"Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"team-kgp-at-semeval-2021-task-7-a-deep-neural","title":"Team\\_KGP at SemEval-2021 Task 7: A Deep Neural System to Detect Humor and Offense with Their Ratings in the Text Data","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tgea-an-error-annotated-dataset-and-benchmark","title":"TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"to-pos-tag-or-not-to-pos-tag-the-impact-of","title":"To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-deep-imitation-learning-for","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","date":"2021-08-01","arxiv_id":"2108.00385","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-map-matching-with-model","title":"Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach","date":"2021-08-01","arxiv_id":"2108.00439","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-encoder-gru-t-e-gru-for-chinese","title":"Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text","date":"2021-08-01","arxiv_id":"2108.00400","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleash-gpt-2-power-for-event-detection","title":"Unleash GPT-2 Power for Event Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-extractive-summarization-based","slug":"unsupervised-extractive-summarization-based","title":"Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"uor-at-semeval-2021-task-4-using-pre-trained","title":"UoR at SemEval-2021 Task 4: Using Pre-trained BERT Token Embeddings for Question Answering of Abstract Meaning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"uor-at-semeval-2021-task-7-utilizing-pre","title":"UoR at SemEval-2021 Task 7: Utilizing Pre-trained DistilBERT Model and Multi-scale CNN for Humor Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"utfpr-at-semeval-2021-task-1-complexity","title":"UTFPR at SemEval-2021 Task 1: Complexity Prediction by Combining BERT Vectors and Classic Features","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"verb-metaphor-detection-via-contextual","title":"Verb Metaphor Detection via Contextual Relation Learning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ynu-hpcc-at-semeval-2021-task-11-using-a-bert","title":"YNU-HPCC at SemEval-2021 Task 11: Using a BERT Model to Extract Contributions from NLP Scholarly Articles","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ynu-hpcc-at-semeval-2021-task-5-using-a","slug":"ynu-hpcc-at-semeval-2021-task-5-using-a","title":"YNU-HPCC at SemEval-2021 Task 5: Using a Transformer-based Model with Auxiliary Information for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ynu-hpcc-at-semeval-2021-task-6-combining","title":"YNU-HPCC at SemEval-2021 Task 6: Combining ALBERT and Text-CNN for Persuasion Detection in Texts and Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"zyj-at-semeval-2021-task-7-hahackathon","title":"ZYJ at SemEval-2021 Task 7: HaHackathon: Detecting and Rating Humor and Offense with ALBERT-Based Model","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"debiasing-samples-from-online-learning-using","title":"Debiasing Samples from Online Learning Using Bootstrap","date":"2021-07-31","arxiv_id":"2108.00236","n_code_links":0,"syntology":null},{"paper":"/paper/opinion-prediction-with-user-fingerprinting","slug":"opinion-prediction-with-user-fingerprinting","title":"Opinion Prediction with User Fingerprinting","date":"2021-07-31","arxiv_id":"2108.00270","n_code_links":1,"syntology":null},{"paper":"/paper/using-knowledge-embedded-attention-to-augment","slug":"using-knowledge-embedded-attention-to-augment","title":"Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition","date":"2021-07-31","arxiv_id":"2108.00194","n_code_links":1,"syntology":null},{"paper":"/paper/dadagp-a-dataset-of-tokenized-guitarpro-songs","slug":"dadagp-a-dataset-of-tokenized-guitarpro-songs","title":"DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models","date":"2021-07-30","arxiv_id":"2107.14653","n_code_links":1,"syntology":null},{"paper":"/paper/dpt-deformable-patch-based-transformer-for","slug":"dpt-deformable-patch-based-transformer-for","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","date":"2021-07-30","arxiv_id":"2107.14467","n_code_links":1,"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":["CASIA-IVA-Lab/DPT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/emailsum-abstractive-email-thread","slug":"emailsum-abstractive-email-thread","title":"EmailSum: Abstractive Email Thread Summarization","date":"2021-07-30","arxiv_id":"2107.14691","n_code_links":1,"syntology":null},{"paper":null,"slug":"learnable-compression-network-with","title":"Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search","date":"2021-07-30","arxiv_id":"2107.14415","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-self-attention-via-vision","slug":"multi-head-self-attention-via-vision","title":"Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning","date":"2021-07-30","arxiv_id":"2108.00045","n_code_links":2,"syntology":null},{"paper":"/paper/perceiver-io-a-general-architecture-for","slug":"perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","arxiv_id":"2107.14795","n_code_links":9,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["deepmind/deepmind-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/product1m-towards-weakly-supervised-instance","slug":"product1m-towards-weakly-supervised-instance","title":"Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining","date":"2021-07-30","arxiv_id":"2107.14572","n_code_links":1,"syntology":null},{"paper":null,"slug":"real-time-streaming-perception-system-for","title":"Real-time Streaming Perception System for Autonomous Driving","date":"2021-07-30","arxiv_id":"2107.14388","n_code_links":0,"syntology":null},{"paper":"/paper/structural-guidance-for-transformer-language","slug":"structural-guidance-for-transformer-language","title":"Structural Guidance for Transformer Language Models","date":"2021-07-30","arxiv_id":"2108.00104","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":10,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["IBM/transformers-struct-guidance"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapting-gpt-gpt-2-and-bert-language-models","title":"Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition","date":"2021-07-29","arxiv_id":"2108.07789","n_code_links":0,"syntology":null},{"paper":"/paper/autotinybert-automatic-hyper-parameter","slug":"autotinybert-automatic-hyper-parameter","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","date":"2021-07-29","arxiv_id":"2107.13686","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-transformer-based-dual","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","date":"2021-07-29","arxiv_id":"2107.13720","n_code_links":0,"syntology":null},{"paper":null,"slug":"ppt-fusion-pyramid-patch-transformerfor-a","title":"PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion","date":"2021-07-29","arxiv_id":"2107.13967","n_code_links":0,"syntology":null},{"paper":"/paper/reformer-the-relational-transformer-for-image","slug":"reformer-the-relational-transformer-for-image","title":"ReFormer: The Relational Transformer for Image Captioning","date":"2021-07-29","arxiv_id":"2107.14178","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-and-improving-relative-position","slug":"rethinking-and-improving-relative-position","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","date":"2021-07-29","arxiv_id":"2107.14222","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":0,"n_instrument":7,"unverified":2,"pointer_only":0,"phrase":"7 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; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/cream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-supervised-transformer-for-multivariate","slug":"self-supervised-transformer-for-multivariate","title":"Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series","date":"2021-07-29","arxiv_id":"2107.14293","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sindhura97/STraTS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"using-perturbed-length-aware-positional","title":"Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation","date":"2021-07-29","arxiv_id":"2107.13689","n_code_links":0,"syntology":null},{"paper":null,"slug":"arabic-aspect-based-sentiment-analysis-using-1","title":"Arabic aspect sentiment polarity classification using BERT","date":"2021-07-28","arxiv_id":"2107.13290","n_code_links":0,"syntology":null},{"paper":"/paper/bi-bimodal-modality-fusion-for-correlation","slug":"bi-bimodal-modality-fusion-for-correlation","title":"Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis","date":"2021-07-28","arxiv_id":"2107.13669","n_code_links":2,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["declare-lab/multimodal-deep-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/goal-oriented-script-construction","slug":"goal-oriented-script-construction","title":"Goal-Oriented Script Construction","date":"2021-07-28","arxiv_id":"2107.13189","n_code_links":1,"syntology":null},{"paper":"/paper/gabert-an-irish-language-model","slug":"gabert-an-irish-language-model","title":"gaBERT -- an Irish Language Model","date":"2021-07-27","arxiv_id":"2107.12930","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-rule-execution-tracking-machine-for","title":"Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation","date":"2021-07-27","arxiv_id":"2107.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"pisltrc-position-informed-sign-language","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","date":"2021-07-27","arxiv_id":"2107.12600","n_code_links":0,"syntology":null},{"paper":"/paper/contextnet-a-click-through-rate-prediction","slug":"contextnet-a-click-through-rate-prediction","title":"ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding","date":"2021-07-26","arxiv_id":"2107.12025","n_code_links":4,"syntology":null},{"paper":"/paper/contextual-transformer-networks-for-visual","slug":"contextual-transformer-networks-for-visual","title":"Contextual Transformer Networks for Visual Recognition","date":"2021-07-26","arxiv_id":"2107.12292","n_code_links":7,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-for-dynamic","slug":"spatial-temporal-transformer-for-dynamic","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","date":"2021-07-26","arxiv_id":"2107.12309","n_code_links":2,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yrcong/sttran"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/go-wider-instead-of-deeper","slug":"go-wider-instead-of-deeper","title":"Go Wider Instead of Deeper","date":"2021-07-25","arxiv_id":"2107.11817","n_code_links":1,"syntology":null},{"paper":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"context-aware-adversarial-training-for-name","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","date":"2021-07-24","arxiv_id":"2107.11610","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdqe-a-more-accurate-direct-pretraining-for","title":"MDQE: A More Accurate Direct Pretraining for Machine Translation Quality Estimation","date":"2021-07-24","arxiv_id":"2107.14600","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-early-sepsis-prediction-with-multi","title":"Improving Early Sepsis Prediction with Multi Modal Learning","date":"2021-07-23","arxiv_id":"2107.11094","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-aware-scheduled-sampling-for","slug":"confidence-aware-scheduled-sampling-for","title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","date":"2021-07-22","arxiv_id":"2107.10427","n_code_links":1,"syntology":null},{"paper":"/paper/ean-event-adaptive-network-for-enhanced","slug":"ean-event-adaptive-network-for-enhanced","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","date":"2021-07-22","arxiv_id":"2107.10771","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization","slug":"evaluating-extractive-summarization","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization-1","slug":"evaluating-extractive-summarization-1","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-contextual-embeddings-on-less","title":"Evaluation of contextual embeddings on less-resourced languages","date":"2021-07-22","arxiv_id":"2107.10614","n_code_links":0,"syntology":null},{"paper":"/paper/fnetar-mixing-tokens-with-autoregressive","slug":"fnetar-mixing-tokens-with-autoregressive","title":"FNetAR: Mixing Tokens with Autoregressive Fourier Transforms","date":"2021-07-22","arxiv_id":"2107.10932","n_code_links":1,"syntology":null},{"paper":"/paper/query2label-a-simple-transformer-way-to-multi","slug":"query2label-a-simple-transformer-way-to-multi","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","date":"2021-07-22","arxiv_id":"2107.10834","n_code_links":3,"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":["SlongLiu/query2labels"],"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":"semantic-text-to-face-gan-st-2fg","title":"Semantic Text-to-Face GAN -ST^2FG","date":"2021-07-22","arxiv_id":"2107.10756","n_code_links":0,"syntology":null},{"paper":null,"slug":"spinning-sequence-to-sequence-models-with","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","date":"2021-07-22","arxiv_id":"2107.10443","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsformer-time-series-transformer-for-tourism","title":"Tsformer: Time series Transformer for tourism demand forecasting","date":"2021-07-22","arxiv_id":"2107.10977","n_code_links":0,"syntology":null},{"paper":"/paper/audio-captioning-transformer","slug":"audio-captioning-transformer","title":"Audio Captioning Transformer","date":"2021-07-21","arxiv_id":"2107.09817","n_code_links":1,"syntology":null},{"paper":null,"slug":"causalbert-injecting-causal-knowledge-into","title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","date":"2021-07-21","arxiv_id":"2107.09852","n_code_links":0,"syntology":null},{"paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","slug":"cyclemlp-a-mlp-like-architecture-for-dense","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","date":"2021-07-21","arxiv_id":"2107.10224","n_code_links":8,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ShoufaChen/CycleMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"digital-einstein-experience-fast-text-to","title":"Digital Einstein Experience: Fast Text-to-Speech for Conversational AI","date":"2021-07-21","arxiv_id":"2107.10658","n_code_links":0,"syntology":null},{"paper":null,"slug":"drdf-determining-the-importance-of-different","title":"DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework","date":"2021-07-21","arxiv_id":"2107.09909","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-text-classification-via-contrastive","title":"Improved Text Classification via Contrastive Adversarial Training","date":"2021-07-21","arxiv_id":"2107.10137","n_code_links":0,"syntology":null},{"paper":"/paper/multi-stream-transformers","slug":"multi-stream-transformers","title":"Multi-Stream Transformers","date":"2021-07-21","arxiv_id":"2107.10342","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-scale-graph-network-with-multi-head","title":"A Multi-scale Graph Network with Multi-head Attention for Histopathology Image Diagnosis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"crew-computation-reuse-and-efficient-weight","title":"CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs","date":"2021-07-20","arxiv_id":"2107.09408","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-video-transformer-can-objects-be","title":"Generative Video Transformer: Can Objects be the Words?","date":"2021-07-20","arxiv_id":"2107.09240","n_code_links":0,"syntology":null},{"paper":"/paper/linked-data-triples-enhance-document","slug":"linked-data-triples-enhance-document","title":"Linked Data Triples Enhance Document Relevance Classification","date":"2021-07-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"weakly-supervised-global-local-feature","title":"Weakly Supervised Global-Local Feature Learning for Cervical Cytology Image Analysis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":"/paper/image-fusion-transformer","slug":"image-fusion-transformer","title":"Image Fusion Transformer","date":"2021-07-19","arxiv_id":"2107.09011","n_code_links":1,"syntology":null},{"paper":"/paper/learning-attributed-graph-representations","slug":"learning-attributed-graph-representations","title":"Learning Attributed Graph Representations with Communicative Message Passing Transformer","date":"2021-07-19","arxiv_id":"2107.08773","n_code_links":1,"syntology":null},{"paper":"/paper/levit-unet-make-faster-encoders-with","slug":"levit-unet-make-faster-encoders-with","title":"LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation","date":"2021-07-19","arxiv_id":"2107.08623","n_code_links":2,"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":["apple1986/LeViT_UNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/long-term-series-forecasting-with-query","slug":"long-term-series-forecasting-with-query","title":"Long-term series forecasting with Query Selector -- efficient model of sparse attention","date":"2021-07-19","arxiv_id":"2107.08687","n_code_links":2,"syntology":null},{"paper":null,"slug":"residual-tree-aggregation-of-layers-for","title":"Residual Tree Aggregation of Layers for Neural Machine Translation","date":"2021-07-19","arxiv_id":"2107.14590","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-piano-transcription-with","slug":"sequence-to-sequence-piano-transcription-with","title":"Sequence-to-Sequence Piano Transcription with Transformers","date":"2021-07-19","arxiv_id":"2107.09142","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a-discriminative-semantic-ranker-for-question","title":"A Discriminative Semantic Ranker for Question Retrieval","date":"2021-07-18","arxiv_id":"2107.08345","n_code_links":0,"syntology":null},{"paper":"/paper/aspect-based-sentiment-analysis-using-bert","slug":"aspect-based-sentiment-analysis-using-bert","title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stock-price-prediction-using-bert-and-gan","title":"Stock price prediction using BERT and GAN","date":"2021-07-18","arxiv_id":"2107.09055","n_code_links":0,"syntology":null},{"paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","slug":"tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-vector-based-approach-to-few-shot-veracity","title":"A Vector-Based Approach to Few-Shot Veracity Classification for Automated Fact-Checking","date":"2021-07-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-transformer-for-efficient-machine","title":"Dynamic Transformer for Efficient Machine Translation on Embedded Devices","date":"2021-07-17","arxiv_id":"2107.08199","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-learning-query-and-product","title":"Neural Search: Learning Query and Product Representations in Fashion E-commerce","date":"2021-07-17","arxiv_id":"2107.08291","n_code_links":0,"syntology":null},{"paper":"/paper/rams-trans-recurrent-attention-multi-scale","slug":"rams-trans-recurrent-attention-multi-scale","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","date":"2021-07-17","arxiv_id":"2107.08192","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-deep-learning-classification","title":"A Comparative Study of Deep Learning Classification Methods on a Small Environmental Microorganism Image Dataset (EMDS-6): from Convolutional Neural Networks to Visual Transformers","date":"2021-07-16","arxiv_id":"2107.07699","n_code_links":0,"syntology":null},{"paper":"/paper/is-attention-to-bounding-boxes-all-you-need","slug":"is-attention-to-bounding-boxes-all-you-need","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","date":"2021-07-16","arxiv_id":"2107.08031","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-law-of-large-documents-understanding-the","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","date":"2021-07-16","arxiv_id":"2107.08128","n_code_links":0,"syntology":null},{"paper":"/paper/autobert-zero-evolving-bert-backbone-from","slug":"autobert-zero-evolving-bert-backbone-from","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","date":"2021-07-15","arxiv_id":"2107.07445","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-task-requirements-writing","slug":"automatic-task-requirements-writing","title":"Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension","date":"2021-07-15","arxiv_id":"2107.07957","n_code_links":1,"syntology":null},{"paper":"/paper/fewclue-a-chinese-few-shot-learning","slug":"fewclue-a-chinese-few-shot-learning","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","date":"2021-07-15","arxiv_id":"2107.07498","n_code_links":1,"syntology":null},{"paper":"/paper/learning-sparse-interaction-graphs-of","slug":"learning-sparse-interaction-graphs-of","title":"Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction","date":"2021-07-15","arxiv_id":"2107.07056","n_code_links":1,"syntology":null},{"paper":"/paper/only-train-once-a-one-shot-neural-network","slug":"only-train-once-a-one-shot-neural-network","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","date":"2021-07-15","arxiv_id":"2107.07467","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-contrastive-learning-with","slug":"self-supervised-contrastive-learning-with","title":"Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks","date":"2021-07-15","arxiv_id":"2107.07610","n_code_links":1,"syntology":null},{"paper":"/paper/star-sparse-transformer-based-action","slug":"star-sparse-transformer-based-action","title":"STAR: Sparse Transformer-based Action Recognition","date":"2021-07-15","arxiv_id":"2107.07089","n_code_links":1,"syntology":null}],"record_sha256":"53d3e108d7898470657c2d16ff9b64d08ced1ee40d8c6264056585678906afa2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}