{"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/228","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":228,"pages_in_order":249,"rows_per_page":100,"rows":[22701,22800],"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/227","next":"/method/multi-head-attention/papers/229","papers":[{"paper":"/paper/gan-bert-generative-adversarial-learning-for","slug":"gan-bert-generative-adversarial-learning-for","title":"GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples","date":"2020-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"generating-medical-reports-from-patient","title":"Generating Medical Reports from Patient-Doctor Conversations Using Sequence-to-Sequence Models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"getting-the-life-out-of-living-how-adequate","title":"Getting the \\#\\#life out of living: How Adequate Are Word-Pieces for Modelling Complex Morphology?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"go-figure-multi-task-transformer-based","title":"Go Figure! Multi-task transformer-based architecture for metaphor detection using idioms: ETS team in 2020 metaphor shared task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"go-wide-then-narrow-efficient-training-of","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","date":"2020-07-01","arxiv_id":"2007.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheme-to-phoneme-conversion-with-a","title":"Grapheme-to-Phoneme Conversion with a Multilingual Transformer Model","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hausamt-v1-0-towards-english-hausa-neural-1","slug":"hausamt-v1-0-towards-english-hausa-neural-1","title":"HausaMT v1.0: Towards English--Hausa Neural Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"how-does-bert-s-attention-change-when-you","title":"How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-to-tame-your-data-data-augmentation-for","title":"How to Tame Your Data: Data Augmentation for Dialog State Tracking","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"illinimet-illinois-system-for-metaphor","title":"IlliniMet: Illinois System for Metaphor Detection with Contextual and Linguistic Information","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-document-level-neural-machine","title":"Improving Document-Level Neural Machine Translation with Domain Adaptation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-multimodal-named-entity-recognition","slug":"improving-multimodal-named-entity-recognition","title":"Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"in-neural-machine-translation-what-does","title":"In Neural Machine Translation, What Does Transfer Learning Transfer?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"information-retrieval-and-extraction-on-covid","title":"Information Retrieval and Extraction on COVID-19 Clinical Articles Using Graph Community Detection and Bio-BERT Embeddings","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning-with-1","title":"Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-operational-risk-classification","title":"Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effect-of-auxiliary","title":"Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"item-based-collaborative-filtering-with-bert","title":"Item-based Collaborative Filtering with BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-training-with-semantic-role-labeling","title":"Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"k-opsala-transition-based-graph-parsing-via","title":"K\\opsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kit-s-iwslt-2020-slt-translation-system","title":"KIT's IWSLT 2020 SLT Translation System","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-principal-parts-for-morphological","title":"Leveraging Principal Parts for Morphological Inflection","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lstm-and-gpt-2-synthetic-speech-transfer","title":"LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity","date":"2020-07-01","arxiv_id":"2007.00659","n_code_links":0,"syntology":null},{"paper":null,"slug":"metaphor-detection-using-contextual-word","title":"Metaphor Detection Using Contextual Word Embeddings From Transformers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"methods-for-extracting-information-from","title":"Methods for Extracting Information from Messages from Primary Care Providers to Specialists","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/modelling-context-and-syntactical-features","slug":"modelling-context-and-syntactical-features","title":"Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-transformer-for-multimodal-machine","slug":"multimodal-transformer-for-multimodal-machine","title":"Multimodal Transformer for Multimodal Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-sarcasm-detection-using-conversation","title":"Neural Sarcasm Detection using Conversation Context","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-transduction-of-letter-position","title":"Neural Transduction of Letter Position Dyslexia using an Anagram Matrix Representation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"oppo-s-machine-translation-system-for-the","title":"OPPO's Machine Translation System for the IWSLT 2020 Open Domain Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"paraphrase-generation-by-learning-how-to-edit","title":"Paraphrase Generation by Learning How to Edit from Samples","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"postech-submission-on-duolingo-shared-task","title":"POSTECH Submission on Duolingo Shared Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-for-referential-information-in","title":"Probing for Referential Information in Language Models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-higher-order-dependency-parsers","title":"Revisiting Higher-Order Dependency Parsers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robertnlp-at-the-iwpt-2020-shared-task","title":"RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-neural-machine-translation-with-asr","title":"Robust Neural Machine Translation with ASR Errors","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/roles-and-utilization-of-attention-heads-in","slug":"roles-and-utilization-of-attention-heads-in","title":"Roles and Utilization of Attention Heads in Transformer-based Neural Language Models","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sarcasm-identification-and-detection-in","title":"Sarcasm Identification and Detection in Conversion Context using BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"self-attention-guided-copy-mechanism-for","title":"Self-Attention Guided Copy Mechanism for Abstractive Summarization","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-context-aware-covid-19","slug":"self-supervised-context-aware-covid-19","title":"Self-supervised context-aware COVID-19 document exploration through atlas grounding","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sentitel-tabsa-for-twitter-reviews-on-uganda","title":"SentiTel: TABSA for Twitter reviews on Uganda Telecoms","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"should-you-fine-tune-bert-for-automated-essay","title":"Should You Fine-Tune BERT for Automated Essay Scoring?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"srpol-s-system-for-the-iwslt-2020-end-to-end","title":"SRPOL's System for the IWSLT 2020 End-to-End Speech Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tbert-topic-models-and-bert-joining-forces","slug":"tbert-topic-models-and-bert-joining-forces","title":"tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-afrl-iwslt-2020-systems-work-from-home","title":"The AFRL IWSLT 2020 Systems: Work-From-Home Edition","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-hw-tsc-video-speech-translation-system-at","title":"The HW-TSC Video Speech Translation System at IWSLT 2020","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-holistic-and-automatic-evaluation-of-1","slug":"towards-holistic-and-automatic-evaluation-of-1","title":"Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-stream-translation-adaptive","title":"Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-and-inference-methods-for-high","title":"Training and Inference Methods for High-Coverage Neural Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-on-sarcasm-detection-with","title":"Transformers on Sarcasm Detection with Context","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-semantic-dependency-parsing-1","slug":"transition-based-semantic-dependency-parsing-1","title":"Transition-based Semantic Dependency Parsing with Pointer Networks","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"turku-enhanced-parser-pipeline-from-raw-text","title":"Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-advertisements-with-bert","title":"Understanding Advertisements with BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"university-of-tsukuba-s-machine-translation","title":"University of Tsukuba's Machine Translation System for IWSLT20 Open Domain Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-faq-retrieval-with-question","title":"Unsupervised FAQ Retrieval with Question Generation and BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-is-penguin-more-similar-to-polar-bear","title":"Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"would-you-rather-a-new-benchmark-for-learning","title":"Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"xiaomi-s-submissions-for-iwslt-2020-open","title":"Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"berters-multimodal-representation-learning","title":"BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer","date":"2020-06-30","arxiv_id":"2007.07229","n_code_links":0,"syntology":null},{"paper":null,"slug":"correction-of-faulty-background-knowledge","title":"Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering","date":"2020-06-30","arxiv_id":"2006.16722","n_code_links":0,"syntology":null},{"paper":"/paper/data-movement-is-all-you-need-a-case-study-of","slug":"data-movement-is-all-you-need-a-case-study-of","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","date":"2020-06-30","arxiv_id":"2007.00072","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spcl/substation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gshard-scaling-giant-models-with-conditional","slug":"gshard-scaling-giant-models-with-conditional","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","date":"2020-06-30","arxiv_id":"2006.16668","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/image-level-harmonization-of-multi-site-data","slug":"image-level-harmonization-of-multi-site-data","title":"Image-level Harmonization of Multi-Site Data using Image-and-Spatial Transformer Networks","date":"2020-06-30","arxiv_id":"2006.16741","n_code_links":1,"syntology":null},{"paper":null,"slug":"se3m-a-model-for-software-effort-estimation","title":"SE3M: A Model for Software Effort Estimation Using Pre-trained Embedding Models","date":"2020-06-30","arxiv_id":"2006.16831","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-approach-for-coreference","title":"Segmentation Approach for Coreference Resolution Task","date":"2020-06-30","arxiv_id":"2007.04301","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-based-joint-encoding-for-1","slug":"a-transformer-based-joint-encoding-for-1","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","date":"2020-06-29","arxiv_id":"2006.15955","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":"/paper/improving-sequence-tagging-for-vietnamese","slug":"improving-sequence-tagging-for-vietnamese","title":"Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models","date":"2020-06-29","arxiv_id":"2006.15994","n_code_links":2,"syntology":null},{"paper":null,"slug":"interpreting-hierarchical-linguistic","title":"Building Interpretable Interaction Trees for Deep NLP Models","date":"2020-06-29","arxiv_id":"2007.04298","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-aware-language-model-pretraining","title":"Knowledge-Aware Language Model Pretraining","date":"2020-06-29","arxiv_id":"2007.00655","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-attention-collaborate-instead-of","slug":"multi-head-attention-collaborate-instead-of","title":"Multi-Head Attention: Collaborate Instead of Concatenate","date":"2020-06-29","arxiv_id":"2006.16362","n_code_links":2,"syntology":null},{"paper":"/paper/predicting-length-of-stay-in-the-intensive","slug":"predicting-length-of-stay-in-the-intensive","title":"Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks","date":"2020-06-29","arxiv_id":"2006.16109","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 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) · 2 unverified","official":{"repos":["EmmaRocheteau/eICU-LoS-prediction"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/simplifying-models-with-unlabeled-output-data","slug":"simplifying-models-with-unlabeled-output-data","title":"Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization","date":"2020-06-29","arxiv_id":"2006.16205","n_code_links":2,"syntology":{"ran":14,"of":14,"n_ran_checked":12,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/composed_finetuning","p-lambda/unlabeled_outputs"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"want-to-identify-extract-and-normalize","title":"Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa","date":"2020-06-29","arxiv_id":"2006.16146","n_code_links":0,"syntology":null},{"paper":"/paper/bond-bert-assisted-open-domain-named-entity","slug":"bond-bert-assisted-open-domain-named-entity","title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","date":"2020-06-28","arxiv_id":"2006.15509","n_code_links":1,"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":["cliang1453/BOND"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bottom-up-human-pose-estimation-by-ranking","slug":"bottom-up-human-pose-estimation-by-ranking","title":"Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates","date":"2020-06-28","arxiv_id":"2006.15480","n_code_links":1,"syntology":null},{"paper":"/paper/progressive-generation-of-long-text","slug":"progressive-generation-of-long-text","title":"Progressive Generation of Long Text with Pretrained Language Models","date":"2020-06-28","arxiv_id":"2006.15720","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":["tanyuqian/progressive-generation"],"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/rethinking-the-positional-encoding-in","slug":"rethinking-the-positional-encoding-in","title":"Rethinking Positional Encoding in Language Pre-training","date":"2020-06-28","arxiv_id":"2006.15595","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: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["guolinke/TUPE"],"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":["listed","official"]}}},{"paper":null,"slug":"self-attention-networks-for-intent-detection-1","title":"Self-Attention Networks for Intent Detection","date":"2020-06-28","arxiv_id":"2006.15585","n_code_links":0,"syntology":null},{"paper":null,"slug":"mind-the-facts-knowledge-boosted-coherent","title":"Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization","date":"2020-06-27","arxiv_id":"2006.15435","n_code_links":0,"syntology":null},{"paper":null,"slug":"normalizador-neural-de-datas-e-enderecos","title":"Normalizador Neural de Datas e Endereços","date":"2020-06-27","arxiv_id":"2007.04300","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-grounded-dialogues-with-pretrained-1","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","date":"2020-06-27","arxiv_id":"2006.15319","n_code_links":0,"syntology":null},{"paper":"/paper/bertology-meets-biology-interpreting","slug":"bertology-meets-biology-interpreting","title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models","date":"2020-06-26","arxiv_id":"2006.15222","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforce/provis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/conditional-set-generation-with-transformers","slug":"conditional-set-generation-with-transformers","title":"Conditional Set Generation with Transformers","date":"2020-06-26","arxiv_id":"2006.16841","n_code_links":1,"syntology":null},{"paper":"/paper/turl-table-understanding-through","slug":"turl-table-understanding-through","title":"TURL: Table Understanding through Representation Learning","date":"2020-06-26","arxiv_id":"2006.14806","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sunlab-osu/TURL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-they-do-when-in-doubt-a-study-of","slug":"what-they-do-when-in-doubt-a-study-of","title":"What they do when in doubt: a study of inductive biases in seq2seq learners","date":"2020-06-26","arxiv_id":"2006.14953","n_code_links":1,"syntology":null},{"paper":"/paper/fastspec-scalable-generation-and-detection-of","slug":"fastspec-scalable-generation-and-detection-of","title":"FastSpec: Scalable Generation and Detection of Spectre Gadgets Using Neural Embeddings","date":"2020-06-25","arxiv_id":"2006.14147","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-source-phrase-representations-for-1","title":"Learning Source Phrase Representations for Neural Machine Translation","date":"2020-06-25","arxiv_id":"2006.14405","n_code_links":0,"syntology":null},{"paper":"/paper/lsbert-a-simple-framework-for-lexical","slug":"lsbert-a-simple-framework-for-lexical","title":"LSBert: A Simple Framework for Lexical Simplification","date":"2020-06-25","arxiv_id":"2006.14939","n_code_links":1,"syntology":null},{"paper":null,"slug":"normalizing-text-using-language-modelling","title":"Normalizing Text using Language Modelling based on Phonetics and String Similarity","date":"2020-06-25","arxiv_id":"2006.14116","n_code_links":0,"syntology":null},{"paper":null,"slug":"sact-self-aware-multi-space-feature","title":"SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning","date":"2020-06-25","arxiv_id":"2006.14262","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-segregating-and-coordinated-segregating","title":"Self-Segregating and Coordinated-Segregating Transformer for Focused Deep Multi-Modular Network for Visual Question Answering","date":"2020-06-25","arxiv_id":"2006.14264","n_code_links":0,"syntology":null},{"paper":"/paper/accelerated-large-batch-optimization-of-bert","slug":"accelerated-large-batch-optimization-of-bert","title":"Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes","date":"2020-06-24","arxiv_id":"2006.13484","n_code_links":1,"syntology":null},{"paper":null,"slug":"differentiable-window-for-dynamic-local-1","title":"Differentiable Window for Dynamic Local Attention","date":"2020-06-24","arxiv_id":"2006.13561","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-constituency-parsing-by-pointing-1","title":"Efficient Constituency Parsing by Pointing","date":"2020-06-24","arxiv_id":"2006.13557","n_code_links":0,"syntology":null},{"paper":"/paper/bach-or-mock-a-grading-function-for-chorales","slug":"bach-or-mock-a-grading-function-for-chorales","title":"Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach","date":"2020-06-23","arxiv_id":"2006.13329","n_code_links":1,"syntology":null},{"paper":"/paper/gaining-insight-into-sars-cov-2-infection-and","slug":"gaining-insight-into-sars-cov-2-infection-and","title":"Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural Networks","date":"2020-06-23","arxiv_id":"2006.12971","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-spatio-temporal-graph-convolutional","title":"Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data","date":"2020-06-23","arxiv_id":"2006.12715","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-edge-features-for-improved","slug":"self-supervised-edge-features-for-improved","title":"Self-supervised edge features for improved Graph Neural Network training","date":"2020-06-23","arxiv_id":"2007.04777","n_code_links":1,"syntology":null},{"paper":"/paper/a-self-attention-network-based-node-embedding","slug":"a-self-attention-network-based-node-embedding","title":"A Self-Attention Network based Node Embedding Model","date":"2020-06-22","arxiv_id":"2006.12100","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-software-naturalness-throughneural","title":"Exploring Software Naturalness through Neural Language Models","date":"2020-06-22","arxiv_id":"2006.12641","n_code_links":0,"syntology":null}],"record_sha256":"1141c45264c6109920fa1e0d8ecca368ab040f9426af2f98dd08161068266358","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}