{"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/linear-layer/papers/241","list_of":"/method/linear-layer","method":"Linear Layer","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":241,"pages_in_order":255,"rows_per_page":100,"rows":[24001,24100],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/240","next":"/method/linear-layer/papers/242","papers":[{"paper":null,"slug":"a-primer-in-bertology-what-we-know-about-how","title":"A Primer in BERTology: What we know about how BERT works","date":"2020-02-27","arxiv_id":"2002.12327","n_code_links":0,"syntology":null},{"paper":null,"slug":"adv-bert-bert-is-not-robust-on-misspellings","title":"Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT","date":"2020-02-27","arxiv_id":"2003.04985","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-large-scale-transformer-based","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","date":"2020-02-27","arxiv_id":"2002.11985","n_code_links":0,"syntology":null},{"paper":"/paper/marathi-to-english-neural-machine-translation","slug":"marathi-to-english-neural-machine-translation","title":"Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers","date":"2020-02-26","arxiv_id":"2002.11643","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-multi-head-attention","title":"Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension","date":"2020-02-26","arxiv_id":"2003.04992","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","n_code_links":1,"syntology":null},{"paper":"/paper/train-large-then-compress-rethinking-model","slug":"train-large-then-compress-rethinking-model","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","date":"2020-02-26","arxiv_id":"2002.11794","n_code_links":2,"syntology":null},{"paper":"/paper/200210957","slug":"200210957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","date":"2020-02-25","arxiv_id":"2002.10957","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-can-see-out-of-the-box-on-the-cross","title":"What BERT Sees: Cross-Modal Transfer for Visual Question Generation","date":"2020-02-25","arxiv_id":"2002.10832","n_code_links":0,"syntology":null},{"paper":"/paper/diversity-based-generalization-for-neural","slug":"diversity-based-generalization-for-neural","title":"Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift","date":"2020-02-25","arxiv_id":"2002.10937","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-bert-parameter-efficiency-on-the","title":"Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0","date":"2020-02-25","arxiv_id":"2002.10670","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-learning-dynamics-of-dnns-via","title":"Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs","date":"2020-02-25","arxiv_id":"2002.10801","n_code_links":0,"syntology":null},{"paper":null,"slug":"fixed-encoder-self-attention-patterns-in","title":"Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation","date":"2020-02-24","arxiv_id":"2002.10260","n_code_links":0,"syntology":null},{"paper":null,"slug":"gret-global-representation-enhanced","title":"GRET: Global Representation Enhanced Transformer","date":"2020-02-24","arxiv_id":"2002.10101","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-fine-tuning-via-self-ensemble","slug":"improving-bert-fine-tuning-via-self-ensemble","title":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","date":"2020-02-24","arxiv_id":"2002.10345","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/predicting-subjective-features-from-questions","slug":"predicting-subjective-features-from-questions","title":"Predicting Subjective Features of Questions of QA Websites using BERT","date":"2020-02-24","arxiv_id":"2002.10107","n_code_links":5,"syntology":null},{"paper":"/paper/sketchformer-transformer-based-representation","slug":"sketchformer-transformer-based-representation","title":"Sketchformer: Transformer-based Representation for Sketched Structure","date":"2020-02-24","arxiv_id":"2002.10381","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":null}},{"paper":null,"slug":"training-question-answering-models-from","title":"Training Question Answering Models From Synthetic Data","date":"2020-02-22","arxiv_id":"2002.09599","n_code_links":0,"syntology":null},{"paper":"/paper/accessing-higher-level-representations-in","slug":"accessing-higher-level-representations-in","title":"Addressing Some Limitations of Transformers with Feedback Memory","date":"2020-02-21","arxiv_id":"2002.09402","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/transformer-sequential"],"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":"/paper/learning-dynamic-knowledge-graphs-to","slug":"learning-dynamic-knowledge-graphs-to","title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","date":"2020-02-21","arxiv_id":"2002.09127","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-hawkes-process","slug":"transformer-hawkes-process","title":"Transformer Hawkes Process","date":"2020-02-21","arxiv_id":"2002.09291","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SimiaoZuo/Transformer-Hawkes-Process"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"federated-pretraining-and-fine-tuning-of-bert","title":"Federated pretraining and fine tuning of BERT using clinical notes from multiple silos","date":"2020-02-20","arxiv_id":"2002.08562","n_code_links":0,"syntology":null},{"paper":"/paper/compressing-bert-studying-the-effects-of-1","slug":"compressing-bert-studying-the-effects-of-1","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","date":"2020-02-19","arxiv_id":"2002.08307","n_code_links":1,"syntology":null},{"paper":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","n_code_links":1,"syntology":null},{"paper":"/paper/molecule-attention-transformer","slug":"molecule-attention-transformer","title":"Molecule Attention Transformer","date":"2020-02-19","arxiv_id":"2002.08264","n_code_links":7,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gmum/MAT"],"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":"/paper/the-microsoft-toolkit-of-multi-task-deep","slug":"the-microsoft-toolkit-of-multi-task-deep","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2020-02-19","arxiv_id":"2002.07972","n_code_links":3,"syntology":null},{"paper":"/paper/toward-making-the-most-of-context-in-neural","slug":"toward-making-the-most-of-context-in-neural","title":"Towards Making the Most of Context in Neural Machine Translation","date":"2020-02-19","arxiv_id":"2002.07982","n_code_links":1,"syntology":null},{"paper":null,"slug":"tree-structured-attention-with-hierarchical-1","title":"Tree-structured Attention with Hierarchical Accumulation","date":"2020-02-19","arxiv_id":"2002.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-self-attention-for-query-based","title":"Conditional Self-Attention for Query-based Summarization","date":"2020-02-18","arxiv_id":"2002.07338","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transform-and-metric-learning-network","title":"Deep Transform and Metric Learning Network: Wedding Deep Dictionary Learning and Neural Networks","date":"2020-02-18","arxiv_id":"2002.07898","n_code_links":0,"syntology":null},{"paper":"/paper/from-english-to-foreign-languages-1","slug":"from-english-to-foreign-languages-1","title":"From English To Foreign Languages: Transferring Pre-trained Language Models","date":"2020-02-18","arxiv_id":"2002.07306","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":null}},{"paper":"/paper/gradient-based-adversarial-training-on","slug":"gradient-based-adversarial-training-on","title":"Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims","date":"2020-02-18","arxiv_id":"2002.07725","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-network-for","slug":"hierarchical-transformer-network-for","title":"Hierarchical Transformer Network for Utterance-level Emotion Recognition","date":"2020-02-18","arxiv_id":"2002.07551","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-latent-knowledge-selection-for-1","slug":"sequential-latent-knowledge-selection-for-1","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","date":"2020-02-18","arxiv_id":"2002.07510","n_code_links":3,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["bckim92/sequential-knowledge-transformer"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/uncertainty-in-structured-prediction","slug":"uncertainty-in-structured-prediction","title":"Uncertainty Estimation in Autoregressive Structured Prediction","date":"2020-02-18","arxiv_id":"2002.07650","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-financial-service-chatbot-based-on-deep","title":"A Financial Service Chatbot based on Deep Bidirectional Transformers","date":"2020-02-17","arxiv_id":"2003.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-computation-versus-quality-for","title":"Controlling Computation versus Quality for Neural Sequence Models","date":"2020-02-17","arxiv_id":"2002.07106","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","n_code_links":3,"syntology":null},{"paper":null,"slug":"low-rank-bottleneck-in-multi-head-attention","title":"Low-Rank Bottleneck in Multi-head Attention Models","date":"2020-02-17","arxiv_id":"2002.07028","n_code_links":0,"syntology":null},{"paper":"/paper/multi-layer-representation-fusion-for-neural-2","slug":"multi-layer-representation-fusion-for-neural-2","title":"Multi-layer Representation Fusion for Neural Machine Translation","date":"2020-02-16","arxiv_id":"2002.06714","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":null}},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":"/paper/sbert-wk-a-sentence-embedding-method-by","slug":"sbert-wk-a-sentence-embedding-method-by","title":"SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models","date":"2020-02-16","arxiv_id":"2002.06652","n_code_links":3,"syntology":null},{"paper":null,"slug":"the-utility-of-general-domain-transfer","title":"The Utility of General Domain Transfer Learning for Medical Language Tasks","date":"2020-02-16","arxiv_id":"2002.06670","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-pretrained-language-models-weight","slug":"fine-tuning-pretrained-language-models-weight","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","date":"2020-02-15","arxiv_id":"2002.06305","n_code_links":4,"syntology":null},{"paper":null,"slug":"small-energy-masking-for-improved-neural","title":"Small energy masking for improved neural network training for end-to-end speech recognition","date":"2020-02-15","arxiv_id":"2002.06312","n_code_links":0,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"deep-attentive-study-session-dropout","title":"Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment","date":"2020-02-14","arxiv_id":"2002.11624","n_code_links":0,"syntology":null},{"paper":"/paper/fquad-french-question-answering-dataset","slug":"fquad-french-question-answering-dataset","title":"FQuAD: French Question Answering Dataset","date":"2020-02-14","arxiv_id":"2002.06071","n_code_links":0,"syntology":null},{"paper":null,"slug":"stress-test-evaluation-of-transformer-based","title":"Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks","date":"2020-02-14","arxiv_id":"2002.06261","n_code_links":0,"syntology":null},{"paper":"/paper/towards-an-appropriate-query-key-and-value","slug":"towards-an-appropriate-query-key-and-value","title":"Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing","date":"2020-02-14","arxiv_id":"2002.07033","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":null}},{"paper":"/paper/transformer-on-a-diet","slug":"transformer-on-a-diet","title":"Transformer on a Diet","date":"2020-02-14","arxiv_id":"2002.06170","n_code_links":1,"syntology":null},{"paper":"/paper/twinbert-distilling-knowledge-to-twin","slug":"twinbert-distilling-knowledge-to-twin","title":"TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval","date":"2020-02-14","arxiv_id":"2002.06275","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-patient-complaint","title":"Understanding patient complaint characteristics using contextual clinical BERT embeddings","date":"2020-02-14","arxiv_id":"2002.05902","n_code_links":0,"syntology":null},{"paper":null,"slug":"cbag-conditional-biomedical-abstract","title":"CBAG: Conditional Biomedical Abstract Generation","date":"2020-02-13","arxiv_id":"2002.05637","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-and-structured-visual-attention-1","slug":"sparse-and-structured-visual-attention-1","title":"Sparse and Structured Visual Attention","date":"2020-02-13","arxiv_id":"2002.05556","n_code_links":1,"syntology":null},{"paper":"/paper/training-large-neural-networks-with-constant","slug":"training-large-neural-networks-with-constant","title":"Training Large Neural Networks with Constant Memory using a New Execution Algorithm","date":"2020-02-13","arxiv_id":"2002.05645","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/attentional-speech-recognition-models","slug":"attentional-speech-recognition-models","title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","date":"2020-02-12","arxiv_id":"2002.05150","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-face-parsing-via-interlinked","slug":"end-to-end-face-parsing-via-interlinked","title":"End-to-End Face Parsing via Interlinked Convolutional Neural Networks","date":"2020-02-12","arxiv_id":"2002.04831","n_code_links":1,"syntology":null},{"paper":"/paper/glu-variants-improve-transformer","slug":"glu-variants-improve-transformer","title":"GLU Variants Improve Transformer","date":"2020-02-12","arxiv_id":"2002.05202","n_code_links":27,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 4 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"learning-to-compare-for-better-training-and","title":"Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models","date":"2020-02-12","arxiv_id":"2002.05058","n_code_links":0,"syntology":null},{"paper":"/paper/on-layer-normalization-in-the-transformer-1","slug":"on-layer-normalization-in-the-transformer-1","title":"On Layer Normalization in the Transformer Architecture","date":"2020-02-12","arxiv_id":"2002.04745","n_code_links":9,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/utilizing-bert-intermediate-layers-for-aspect","slug":"utilizing-bert-intermediate-layers-for-aspect","title":"Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference","date":"2020-02-12","arxiv_id":"2002.04815","n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-consistency-regularization-for-gans","title":"Improved Consistency Regularization for GANs","date":"2020-02-11","arxiv_id":"2002.04724","n_code_links":0,"syntology":null},{"paper":null,"slug":"superbloom-bloom-filter-meets-transformer-1","title":"Superbloom: Bloom filter meets Transformer","date":"2020-02-11","arxiv_id":"2002.04723","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-with-streaming-annotation","title":"Training with Streaming Annotation","date":"2020-02-11","arxiv_id":"2002.04165","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-representation-learning-for-dynamical","title":"Deep Representation Learning for Dynamical Systems Modeling","date":"2020-02-10","arxiv_id":"2002.05111","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-multi-speaker-speech-recognition-1","title":"End-to-End Multi-speaker Speech Recognition with Transformer","date":"2020-02-10","arxiv_id":"2002.03921","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-alignment-of-contextual-word-1","slug":"multilingual-alignment-of-contextual-word-1","title":"Multilingual Alignment of Contextual Word Representations","date":"2020-02-10","arxiv_id":"2002.03518","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":null}},{"paper":null,"slug":"pre-training-tasks-for-embedding-based-large","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","date":"2020-02-10","arxiv_id":"2002.03932","n_code_links":0,"syntology":null},{"paper":null,"slug":"stickypillars-robust-feature-matching-on","title":"StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks","date":"2020-02-10","arxiv_id":"2002.03983","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-pre-training-models-in-named","title":"Application of Pre-training Models in Named Entity Recognition","date":"2020-02-09","arxiv_id":"2002.08902","n_code_links":0,"syntology":null},{"paper":null,"slug":"momentum-improves-normalized-sgd","title":"Momentum Improves Normalized SGD","date":"2020-02-09","arxiv_id":"2002.03305","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-distance-between-two-neural-networks","slug":"on-the-distance-between-two-neural-networks","title":"On the distance between two neural networks and the stability of learning","date":"2020-02-09","arxiv_id":"2002.03432","n_code_links":2,"syntology":null},{"paper":"/paper/blank-language-models","slug":"blank-language-models","title":"Blank Language Models","date":"2020-02-08","arxiv_id":"2002.03079","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":1,"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":["Varal7/blank_language_model"],"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/bert-of-theseus-compressing-bert-by","slug":"bert-of-theseus-compressing-bert-by","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","date":"2020-02-07","arxiv_id":"2002.02925","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["JetRunner/BERT-of-Theseus"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"multimodal-matching-transformer-for-live","title":"Multimodal Matching Transformer for Live Commenting","date":"2020-02-07","arxiv_id":"2002.02649","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-capsule-model-for-intent","slug":"transformer-capsule-model-for-intent","title":"Transformer-Capsule Model for Intent Detection","date":"2020-02-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transformer-transducer-a-streamable-speech","slug":"transformer-transducer-a-streamable-speech","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","date":"2020-02-07","arxiv_id":"2002.02562","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/few-shot-learning-as-domain-adaptation","slug":"few-shot-learning-as-domain-adaptation","title":"Few-Shot Learning as Domain Adaptation: Algorithm and Analysis","date":"2020-02-06","arxiv_id":"2002.02050","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-hierarchical-fine-grained-prosody","title":"Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis","date":"2020-02-06","arxiv_id":"2002.03785","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-aspects-of-creativity-in","slug":"introducing-aspects-of-creativity-in","title":"Introducing Aspects of Creativity in Automatic Poetry Generation","date":"2020-02-06","arxiv_id":"2002.02511","n_code_links":1,"syntology":null},{"paper":null,"slug":"perm2vec-graph-permutation-selection-for","title":"perm2vec: Graph Permutation Selection for Decoding of Error Correction Codes using Self-Attention","date":"2020-02-06","arxiv_id":"2002.02315","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-the-pretraining-and-finetuning","title":"Aligning the Pretraining and Finetuning Objectives of Language Models","date":"2020-02-05","arxiv_id":"2002.02000","n_code_links":0,"syntology":null},{"paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","slug":"k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","arxiv_id":"2002.01808","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":6,"n_instrument":5,"unverified":3,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/rapid-adaptation-of-bert-for-information","slug":"rapid-adaptation-of-bert-for-information","title":"Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents","date":"2020-02-05","arxiv_id":"2002.01861","n_code_links":1,"syntology":null},{"paper":"/paper/vocoder-free-end-to-end-voice-conversion-with","slug":"vocoder-free-end-to-end-voice-conversion-with","title":"Vocoder-free End-to-End Voice Conversion with Transformer Network","date":"2020-02-05","arxiv_id":"2002.03808","n_code_links":1,"syntology":null},{"paper":"/paper/interpretable-time-budget-constrained","slug":"interpretable-time-budget-constrained","title":"Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking","date":"2020-02-04","arxiv_id":"2002.01854","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-long-and-short-term-user-literal","title":"Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption","date":"2020-02-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multistage-model-for-robust-face-alignment","title":"Multistage Model for Robust Face Alignment Using Deep Neural Networks","date":"2020-02-04","arxiv_id":"2002.01075","n_code_links":0,"syntology":null},{"paper":"/paper/bertrand-dr-improving-text-to-sql-using-a","slug":"bertrand-dr-improving-text-to-sql-using-a","title":"Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker","date":"2020-02-03","arxiv_id":"2002.00557","n_code_links":1,"syntology":null},{"paper":"/paper/iart-intent-aware-response-ranking-with","slug":"iart-intent-aware-response-ranking-with","title":"IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems","date":"2020-02-03","arxiv_id":"2002.00571","n_code_links":1,"syntology":null},{"paper":"/paper/beat-the-ai-investigating-adversarial-human","slug":"beat-the-ai-investigating-adversarial-human","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","date":"2020-02-02","arxiv_id":"2002.00293","n_code_links":1,"syntology":null},{"paper":"/paper/wavetts-tacotron-based-tts-with-joint-time","slug":"wavetts-tacotron-based-tts-with-joint-time","title":"WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss","date":"2020-02-02","arxiv_id":"2002.00417","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-text-and-video-a-universal","slug":"bridging-text-and-video-a-universal","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","date":"2020-02-01","arxiv_id":"2002.00163","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"fine-tuning-bert-for-schema-guided-zero-shot","title":"Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking","date":"2020-02-01","arxiv_id":"2002.00181","n_code_links":0,"syntology":null},{"paper":"/paper/pop-music-transformer-generating-music-with","slug":"pop-music-transformer-generating-music-with","title":"Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions","date":"2020-02-01","arxiv_id":"2002.00212","n_code_links":7,"syntology":null},{"paper":"/paper/pretrained-transformers-for-simple-question","slug":"pretrained-transformers-for-simple-question","title":"Pretrained Transformers for Simple Question Answering over Knowledge Graphs","date":"2020-01-31","arxiv_id":"2001.11985","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstructing-natural-scenes-from-fmri","title":"Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN","date":"2020-01-31","arxiv_id":"2001.11761","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-training-for-aspect-based","slug":"adversarial-training-for-aspect-based","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","date":"2020-01-30","arxiv_id":"2001.11316","n_code_links":4,"syntology":null},{"paper":null,"slug":"do-we-need-word-order-information-for-cross","title":"On the Importance of Word Order Information in Cross-lingual Sequence Labeling","date":"2020-01-30","arxiv_id":"2001.11164","n_code_links":0,"syntology":null}],"record_sha256":"c7981f505050bf8ae88bf690d8359ca326ab05e4050b69dfac2ae6af385f50b3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}