{"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/296","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":296,"pages_in_order":316,"rows_per_page":100,"rows":[29501,29600],"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/295","next":"/method/attention/papers/297","papers":[{"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},{"paper":"/paper/reco-a-large-scale-chinese-reading","slug":"reco-a-large-scale-chinese-reading","title":"ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion","date":"2020-06-22","arxiv_id":"2006.12146","n_code_links":1,"syntology":null},{"paper":"/paper/students-need-more-attention-bert-based","slug":"students-need-more-attention-bert-based","title":"Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage","date":"2020-06-22","arxiv_id":"2006.11991","n_code_links":1,"syntology":null},{"paper":"/paper/a-universal-representation-transformer-layer","slug":"a-universal-representation-transformer-layer","title":"A Universal Representation Transformer Layer for Few-Shot Image Classification","date":"2020-06-21","arxiv_id":"2006.11702","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-learning-rates-with-maximum","slug":"adaptive-learning-rates-with-maximum","title":"MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients","date":"2020-06-21","arxiv_id":"2006.11918","n_code_links":1,"syntology":null},{"paper":"/paper/advaug-robust-adversarial-augmentation-for-1","slug":"advaug-robust-adversarial-augmentation-for-1","title":"AdvAug: Robust Adversarial Augmentation for Neural Machine Translation","date":"2020-06-21","arxiv_id":"2006.11834","n_code_links":0,"syntology":null},{"paper":null,"slug":"off-policy-self-critical-training-for","title":"Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation","date":"2020-06-21","arxiv_id":"2006.11714","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nyu-cuboulder-systems-for-sigmorphon-2020-1","title":"The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2","date":"2020-06-21","arxiv_id":"2006.11830","n_code_links":0,"syntology":null},{"paper":"/paper/memory-transformer","slug":"memory-transformer","title":"Memory Transformer","date":"2020-06-20","arxiv_id":"2006.11527","n_code_links":1,"syntology":null},{"paper":null,"slug":"sarcasm-detection-in-tweets-with-bert-and-1","title":"Sarcasm Detection in Tweets with BERT and GloVe Embeddings","date":"2020-06-20","arxiv_id":"2006.11512","n_code_links":0,"syntology":null},{"paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","slug":"wav2vec-2-0-a-framework-for-self-supervised","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","date":"2020-06-20","arxiv_id":"2006.11477","n_code_links":25,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pytorch/fairseq"],"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/a-qualitative-evaluation-of-language-models","slug":"a-qualitative-evaluation-of-language-models","title":"A Qualitative Evaluation of Language Models on Automatic Question-Answering for COVID-19","date":"2020-06-19","arxiv_id":"2006.10964","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-deep-metamodeling-to-calibrate-and","title":"End-to-end deep metamodeling to calibrate and optimize energy loads","date":"2020-06-19","arxiv_id":"2006.12390","n_code_links":0,"syntology":null},{"paper":"/paper/new-vietnamese-corpus-for-machine","slug":"new-vietnamese-corpus-for-machine","title":"New Vietnamese Corpus for Machine Reading Comprehension of Health News Articles","date":"2020-06-19","arxiv_id":"2006.11138","n_code_links":0,"syntology":null},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","n_code_links":6,"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":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"boosting-objective-scores-of-speech","title":"Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing","date":"2020-06-18","arxiv_id":"2006.10296","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-enabled-semantic-communication","slug":"deep-learning-enabled-semantic-communication","title":"Deep Learning Enabled Semantic Communication Systems","date":"2020-06-18","arxiv_id":"2006.10685","n_code_links":1,"syntology":null},{"paper":"/paper/i-bert-inductive-generalization-of","slug":"i-bert-inductive-generalization-of","title":"I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths","date":"2020-06-18","arxiv_id":"2006.10220","n_code_links":1,"syntology":null},{"paper":"/paper/infinite-attention-nngp-and-ntk-for-deep","slug":"infinite-attention-nngp-and-ntk-for-deep","title":"Infinite attention: NNGP and NTK for deep attention networks","date":"2020-06-18","arxiv_id":"2006.10540","n_code_links":1,"syntology":null},{"paper":"/paper/multi-branch-attentive-transformer","slug":"multi-branch-attentive-transformer","title":"Multi-branch Attentive Transformer","date":"2020-06-18","arxiv_id":"2006.10270","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"seal-segment-wise-extractive-abstractive-long","title":"SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization","date":"2020-06-18","arxiv_id":"2006.10213","n_code_links":0,"syntology":null},{"paper":"/paper/senwave-monitoring-the-global-sentiments","slug":"senwave-monitoring-the-global-sentiments","title":"SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic","date":"2020-06-18","arxiv_id":"2006.10842","n_code_links":2,"syntology":null},{"paper":"/paper/sparse-gpu-kernels-for-deep-learning","slug":"sparse-gpu-kernels-for-deep-learning","title":"Sparse GPU Kernels for Deep Learning","date":"2020-06-18","arxiv_id":"2006.10901","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatically-ranked-russian-paraphrase","title":"Automatically Ranked Russian Paraphrase Corpus for Text Generation","date":"2020-06-17","arxiv_id":"2006.09719","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-bert-cross-lingual","title":"Exploring the BERT Cross-Lingual Transferability: a Case Study in Reading Comprehension","date":"2020-06-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-protection-classification-of","title":"Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers","date":"2020-06-17","arxiv_id":"2006.09865","n_code_links":0,"syntology":null},{"paper":"/paper/learning-visual-commonsense-for-robust-scene","slug":"learning-visual-commonsense-for-robust-scene","title":"Learning Visual Commonsense for Robust Scene Graph Generation","date":"2020-06-17","arxiv_id":"2006.09623","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":null}},{"paper":"/paper/tagging-and-parsing-of-multidomain","slug":"tagging-and-parsing-of-multidomain","title":"Tagging and parsing of multidomain collections","date":"2020-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-retrieval-for-iterative-self","slug":"cross-lingual-retrieval-for-iterative-self","title":"Cross-lingual Retrieval for Iterative Self-Supervised Training","date":"2020-06-16","arxiv_id":"2006.09526","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-code-switching-language-models-for","title":"End-to-End Code Switching Language Models for Automatic Speech Recognition","date":"2020-06-16","arxiv_id":"2006.08870","n_code_links":0,"syntology":null},{"paper":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-pipeline-parallel-dnn","slug":"memory-efficient-pipeline-parallel-dnn","title":"Memory-Efficient Pipeline-Parallel DNN Training","date":"2020-06-16","arxiv_id":"2006.09503","n_code_links":1,"syntology":{"ran":2,"of":10,"n_ran_checked":2,"n_instrument":0,"unverified":8,"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) · 8 unverified","official":null}},{"paper":"/paper/modeling-graph-structure-via-relative","slug":"modeling-graph-structure-via-relative","title":"Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs","date":"2020-06-16","arxiv_id":"2006.09242","n_code_links":0,"syntology":null},{"paper":"/paper/perl-pivot-based-domain-adaptation-for-pre","slug":"perl-pivot-based-domain-adaptation-for-pre","title":"PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models","date":"2020-06-16","arxiv_id":"2006.09075","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-cross-lingual-pivots-to-model","title":"Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation","date":"2020-06-16","arxiv_id":"2006.08881","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-sppd-system-for-schema-guided-dialogue","title":"The SPPD System for Schema Guided Dialogue State Tracking Challenge","date":"2020-06-16","arxiv_id":"2006.09035","n_code_links":0,"syntology":null},{"paper":null,"slug":"cooking-is-all-about-people-comment","title":"Cooking Is All About People: Comment Classification On Cookery Channels Using BERT and Classification Models (Malayalam-English Mix-Code)","date":"2020-06-15","arxiv_id":"2007.04249","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentiable-neural-architecture","title":"Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement","date":"2020-06-15","arxiv_id":"2006.08231","n_code_links":0,"syntology":null},{"paper":"/paper/document-classification-for-covid-19","slug":"document-classification-for-covid-19","title":"Document Classification for COVID-19 Literature","date":"2020-06-15","arxiv_id":"2006.13816","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploration-of-end-to-end-asr-for-openstt","title":"Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset","date":"2020-06-15","arxiv_id":"2006.08274","n_code_links":0,"syntology":null},{"paper":"/paper/finbert-a-pretrained-language-model-for","slug":"finbert-a-pretrained-language-model-for","title":"FinBERT: A Pretrained Language Model for Financial Communications","date":"2020-06-15","arxiv_id":"2006.08097","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yya518/FinBERT"],"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":"/paper/fine-grained-human-evaluation-of-transformer","slug":"fine-grained-human-evaluation-of-transformer","title":"Fine-grained Human Evaluation of Transformer and Recurrent Approaches to Neural Machine Translation for English-to-Chinese","date":"2020-06-15","arxiv_id":"2006.08297","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-image-summarization-textual-summary","title":"Multi-Image Summarization: Textual Summary from a Set of Cohesive Images","date":"2020-06-15","arxiv_id":"2006.08686","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-multi-property-extraction-and-beyond","title":"On the Multi-Property Extraction and Beyond","date":"2020-06-15","arxiv_id":"2006.08281","n_code_links":0,"syntology":null},{"paper":null,"slug":"finest-bert-and-crosloengual-bert-less-is","title":"FinEst BERT and CroSloEngual BERT: less is more in multilingual models","date":"2020-06-14","arxiv_id":"2006.07890","n_code_links":0,"syntology":null},{"paper":null,"slug":"guided-transformer-leveraging-multiple","title":"Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search","date":"2020-06-13","arxiv_id":"2006.07548","n_code_links":0,"syntology":null},{"paper":"/paper/modelling-high-level-mathematical-reasoning","slug":"modelling-high-level-mathematical-reasoning","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","date":"2020-06-13","arxiv_id":"2006.09265","n_code_links":2,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 1 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) · 6 unverified","official":null}},{"paper":null,"slug":"temporal-fusion-network-for-temporal-action","title":"Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)","date":"2020-06-13","arxiv_id":"2006.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-monolingual-model-to-low","title":"Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya","date":"2020-06-13","arxiv_id":"2006.07698","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-natural-language-processing","title":"Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech","date":"2020-06-12","arxiv_id":"2006.07358","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-the-inductive-biases-of","slug":"unmasking-the-inductive-biases-of","title":"Benchmarking Unsupervised Object Representations for Video Sequences","date":"2020-06-12","arxiv_id":"2006.07034","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ecker-lab/object-centric-representation-benchmark"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-monolingual-approach-to-contextualized-word","slug":"a-monolingual-approach-to-contextualized-word","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","date":"2020-06-11","arxiv_id":"2006.06202","n_code_links":0,"syntology":null},{"paper":"/paper/dance-revolution-long-sequence-dance","slug":"dance-revolution-long-sequence-dance","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","date":"2020-06-11","arxiv_id":"2006.06119","n_code_links":0,"syntology":null},{"paper":"/paper/fastpitch-parallel-text-to-speech-with-pitch","slug":"fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","date":"2020-06-11","arxiv_id":"2006.06873","n_code_links":6,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["NVIDIA/DeepLearningExamples"],"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":["listed","named_in_paper"]}}},{"paper":null,"slug":"implicit-kernel-attention","title":"Implicit Kernel Attention","date":"2020-06-11","arxiv_id":"2006.06147","n_code_links":0,"syntology":null},{"paper":"/paper/traffic-transformer-capturing-the-continuity","slug":"traffic-transformer-capturing-the-continuity","title":"Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting","date":"2020-06-11","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extrapolation-for-large-batch-training-in","title":"Extrapolation for Large-batch Training in Deep Learning","date":"2020-06-10","arxiv_id":"2006.05720","n_code_links":0,"syntology":null},{"paper":"/paper/mc-bert-efficient-language-pre-training-via-a","slug":"mc-bert-efficient-language-pre-training-via-a","title":"MC-BERT: Efficient Language Pre-Training via a Meta Controller","date":"2020-06-10","arxiv_id":"2006.05744","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["MC-BERT/MC-BERT"],"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":["official"]}}},{"paper":"/paper/revisiting-few-sample-bert-fine-tuning","slug":"revisiting-few-sample-bert-fine-tuning","title":"Revisiting Few-sample BERT Fine-tuning","date":"2020-06-10","arxiv_id":"2006.05987","n_code_links":1,"syntology":null},{"paper":null,"slug":"dyhgcn-a-dynamic-heterogeneous-graph","title":"DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction","date":"2020-06-09","arxiv_id":"2006.05169","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-generative-conversational-query","slug":"few-shot-generative-conversational-query","title":"Few-Shot Generative Conversational Query Rewriting","date":"2020-06-09","arxiv_id":"2006.05009","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp/ConversationQueryRewriter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"graph-aware-transformer-is-attention-all","title":"Graph-Aware Transformer: Is Attention All Graphs Need?","date":"2020-06-09","arxiv_id":"2006.05213","n_code_links":0,"syntology":null},{"paper":null,"slug":"hausamt-v1-0-towards-english-hausa-neural","title":"HausaMT v1.0: Towards English-Hausa Neural Machine Translation","date":"2020-06-09","arxiv_id":"2006.05014","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paraphrase-generation-using-pre","title":"Unsupervised Paraphrase Generation using Pre-trained Language Models","date":"2020-06-09","arxiv_id":"2006.05477","n_code_links":0,"syntology":null},{"paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","slug":"fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","arxiv_id":"2006.04558","n_code_links":37,"syntology":{"ran":83,"of":119,"n_ran_checked":73,"n_instrument":10,"unverified":36,"pointer_only":40,"phrase":"83 ran (of which 27 constructed an object rather than computing a result; 73 with no instrument failure: 9 honoured, 1 violated, 63 with no contract checked; 10 where Syntology's instrument failed) · 36 unverified","official":null}},{"paper":"/paper/learning-to-count-words-in-fluent-speech","slug":"learning-to-count-words-in-fluent-speech","title":"Learning to Count Words in Fluent Speech enables Online Speech Recognition","date":"2020-06-08","arxiv_id":"2006.04928","n_code_links":1,"syntology":null},{"paper":"/paper/linformer-self-attention-with-linear","slug":"linformer-self-attention-with-linear","title":"Linformer: Self-Attention with Linear Complexity","date":"2020-06-08","arxiv_id":"2006.04768","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/fairseq"],"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":["listed","unlocated"]}}},{"paper":null,"slug":"modeling-discourse-structure-for-document","title":"Modeling Discourse Structure for Document-level Neural Machine Translation","date":"2020-06-08","arxiv_id":"2006.04721","n_code_links":0,"syntology":null},{"paper":"/paper/multispeech-multi-speaker-text-to-speech-with","slug":"multispeech-multi-speaker-text-to-speech-with","title":"MultiSpeech: Multi-Speaker Text to Speech with Transformer","date":"2020-06-08","arxiv_id":"2006.04664","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":null}},{"paper":null,"slug":"o-n-connections-are-expressive-enough","title":"$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers","date":"2020-06-08","arxiv_id":"2006.04862","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-stability-of-fine-tuning-bert","slug":"on-the-stability-of-fine-tuning-bert","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","date":"2020-06-08","arxiv_id":"2006.04884","n_code_links":2,"syntology":{"ran":13,"of":20,"n_ran_checked":9,"n_instrument":4,"unverified":7,"pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["uds-lsv/bert-stable-fine-tuning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/wat-zei-je-detecting-out-of-distribution","slug":"wat-zei-je-detecting-out-of-distribution","title":"Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers","date":"2020-06-08","arxiv_id":"2006.08344","n_code_links":1,"syntology":null},{"paper":"/paper/bert-loses-patience-fast-and-robust-inference","slug":"bert-loses-patience-fast-and-robust-inference","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","date":"2020-06-07","arxiv_id":"2006.04152","n_code_links":1,"syntology":null},{"paper":"/paper/learning-texture-transformer-network-for-1","slug":"learning-texture-transformer-network-for-1","title":"Learning Texture Transformer Network for Image Super-Resolution","date":"2020-06-07","arxiv_id":"2006.04139","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["researchmm/TTSR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"medical-concept-normalization-in-user","title":"Medical Concept Normalization in User Generated Texts by Learning Target Concept Embeddings","date":"2020-06-07","arxiv_id":"2006.04014","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-polish-transformer-based","slug":"pre-training-polish-transformer-based","title":"Pre-training Polish Transformer-based Language Models at Scale","date":"2020-06-07","arxiv_id":"2006.04229","n_code_links":1,"syntology":null},{"paper":null,"slug":"challenges-and-thrills-of-legal-arguments","title":"Challenges and Thrills of Legal Arguments","date":"2020-06-06","arxiv_id":"2006.03773","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-natural-language-understanding","slug":"accelerating-natural-language-understanding","title":"Accelerating Natural Language Understanding in Task-Oriented Dialog","date":"2020-06-05","arxiv_id":"2006.03701","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-overview-of-neural-network-compression","title":"An Overview of Neural Network Compression","date":"2020-06-05","arxiv_id":"2006.03669","n_code_links":0,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","n_code_links":14,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["microsoft/DeBERTa"],"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":["listed","named_in_paper","unlocated"]}}},{"paper":"/paper/funnel-transformer-filtering-out-sequential","slug":"funnel-transformer-filtering-out-sequential","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","date":"2020-06-05","arxiv_id":"2006.03236","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":["laiguokun/Funnel-Transformer"],"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":"/paper/gmat-global-memory-augmentation-for","slug":"gmat-global-memory-augmentation-for","title":"GMAT: Global Memory Augmentation for Transformers","date":"2020-06-05","arxiv_id":"2006.03274","n_code_links":1,"syntology":null},{"paper":"/paper/masked-language-modeling-for-proteins-via","slug":"masked-language-modeling-for-proteins-via","title":"Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers","date":"2020-06-05","arxiv_id":"2006.03555","n_code_links":1,"syntology":null},{"paper":null,"slug":"udpipe-at-evalatin-2020-contextualized-1","title":"UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings","date":"2020-06-05","arxiv_id":"2006.03687","n_code_links":0,"syntology":null}],"record_sha256":"0446e6d3742b398da80c9c7499a971e154edc7882f010cdb1a325a779ce1748a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}