{"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/transformer/papers/133","list_of":"/method/transformer","method":"Transformer","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":133,"pages_in_order":140,"rows_per_page":100,"rows":[13201,13300],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/132","next":"/method/transformer/papers/134","papers":[{"paper":null,"slug":"relational-learning-between-multiple","title":"Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers","date":"2020-04-12","arxiv_id":"2004.05640","n_code_links":0,"syntology":null},{"paper":null,"slug":"stacked-convolutional-deep-encoding-network","title":"Stacked Convolutional Deep Encoding Network for Video-Text Retrieval","date":"2020-04-10","arxiv_id":"2004.04959","n_code_links":0,"syntology":null},{"paper":null,"slug":"telling-bert-s-full-story-from-local","title":"Telling BERT's full story: from Local Attention to Global Aggregation","date":"2020-04-10","arxiv_id":"2004.05916","n_code_links":0,"syntology":null},{"paper":"/paper/cortical-surface-registration-using","slug":"cortical-surface-registration-using","title":"Cortical surface registration using unsupervised learning","date":"2020-04-09","arxiv_id":"2004.04617","n_code_links":1,"syntology":null},{"paper":"/paper/on-optimal-transformer-depth-for-low-resource","slug":"on-optimal-transformer-depth-for-low-resource","title":"On Optimal Transformer Depth for Low-Resource Language Translation","date":"2020-04-09","arxiv_id":"2004.04418","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequential-neural-rendering-with-transformer","title":"Sequential View Synthesis with Transformer","date":"2020-04-09","arxiv_id":"2004.04548","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-transformers-in-rl","slug":"adaptive-transformers-in-rl","title":"Adaptive Transformers in RL","date":"2020-04-08","arxiv_id":"2004.03761","n_code_links":1,"syntology":null},{"paper":"/paper/diverse-controllable-and-keyphrase-aware-a","slug":"diverse-controllable-and-keyphrase-aware-a","title":"Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation","date":"2020-04-08","arxiv_id":"2004.03875","n_code_links":1,"syntology":null},{"paper":"/paper/poor-man-s-bert-smaller-and-faster","slug":"poor-man-s-bert-smaller-and-faster","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","date":"2020-04-08","arxiv_id":"2004.03844","n_code_links":4,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hsajjad/transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/byte-pair-encoding-is-suboptimal-for-language","slug":"byte-pair-encoding-is-suboptimal-for-language","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","date":"2020-04-07","arxiv_id":"2004.03720","n_code_links":1,"syntology":null},{"paper":"/paper/probabilistic-spatial-transformers-for","slug":"probabilistic-spatial-transformers-for","title":"Probabilistic Spatial Transformer Networks","date":"2020-04-07","arxiv_id":"2004.03637","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-to-learn-hierarchical-contexts","slug":"transformers-to-learn-hierarchical-contexts","title":"Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering","date":"2020-04-07","arxiv_id":"2004.03561","n_code_links":1,"syntology":null},{"paper":"/paper/a-systematic-analysis-of-morphological","slug":"a-systematic-analysis-of-morphological","title":"A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages","date":"2020-04-06","arxiv_id":"2004.03032","n_code_links":1,"syntology":null},{"paper":"/paper/autotoon-automatic-geometric-warping-for-face","slug":"autotoon-automatic-geometric-warping-for-face","title":"AutoToon: Automatic Geometric Warping for Face Cartoon Generation","date":"2020-04-06","arxiv_id":"2004.02377","n_code_links":1,"syntology":null},{"paper":null,"slug":"syntax-driven-iterative-expansion-language","title":"Syntax-driven Iterative Expansion Language Models for Controllable Text Generation","date":"2020-04-05","arxiv_id":"2004.02211","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-question-reformulation-via","title":"Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models","date":"2020-04-04","arxiv_id":"2004.01909","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-abstractive-summarization-for","slug":"end-to-end-abstractive-summarization-for","title":"A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining","date":"2020-04-04","arxiv_id":"2004.02016","n_code_links":3,"syntology":null},{"paper":null,"slug":"step-sequence-to-sequence-transformer-pre","title":"Pre-training for Abstractive Document Summarization by Reinstating Source Text","date":"2020-04-04","arxiv_id":"2004.01853","n_code_links":0,"syntology":null},{"paper":"/paper/lidar-based-online-3d-video-object-detection","slug":"lidar-based-online-3d-video-object-detection","title":"LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention","date":"2020-04-03","arxiv_id":"2004.01389","n_code_links":1,"syntology":null},{"paper":null,"slug":"testing-pre-trained-transformer-models-for","title":"Testing pre-trained Transformer models for Lithuanian news clustering","date":"2020-04-03","arxiv_id":"2004.03461","n_code_links":0,"syntology":null},{"paper":null,"slug":"dstc8-avsd-multimodal-semantic-transformer","title":"DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator","date":"2020-04-01","arxiv_id":"2004.08299","n_code_links":0,"syntology":null},{"paper":"/paper/sign-language-translation-with-transformers","slug":"sign-language-translation-with-transformers","title":"Better Sign Language Translation with STMC-Transformer","date":"2020-04-01","arxiv_id":"2004.00588","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kayoyin/transformer-slt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-swiss-german-dictionary-variation-in-speech","title":"A Swiss German Dictionary: Variation in Speech and Writing","date":"2020-03-31","arxiv_id":"2004.00139","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepsumm-deep-code-summaries-using-neural","title":"DeepSumm -- Deep Code Summaries using Neural Transformer Architecture","date":"2020-03-31","arxiv_id":"2004.00998","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-enhanced-representation-learning-for","title":"Graph Enhanced Representation Learning for News Recommendation","date":"2020-03-31","arxiv_id":"2003.14292","n_code_links":0,"syntology":null},{"paper":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-hierarchical-transformer-for-unsupervised","title":"A Hierarchical Transformer for Unsupervised Parsing","date":"2020-03-30","arxiv_id":"2003.13841","n_code_links":0,"syntology":null},{"paper":null,"slug":"ariel-volume-coding-for-sentence-generation","title":"AriEL: volume coding for sentence generation","date":"2020-03-30","arxiv_id":"2003.13600","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-contextualized-sentence","title":"Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation","date":"2020-03-30","arxiv_id":"2003.13205","n_code_links":0,"syntology":null},{"paper":"/paper/sign-language-transformers-joint-end-to-end","slug":"sign-language-transformers-joint-end-to-end","title":"Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation","date":"2020-03-30","arxiv_id":"2003.13830","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["neccam/slt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/abstractive-text-summarization-based-on","slug":"abstractive-text-summarization-based-on","title":"Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling","date":"2020-03-29","arxiv_id":"2003.13027","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["axenov/BERT-Summ-OpenNMT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/recursive-non-autoregressive-graph-to-graph","slug":"recursive-non-autoregressive-graph-to-graph","title":"Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement","date":"2020-03-29","arxiv_id":"2003.13118","n_code_links":1,"syntology":null},{"paper":null,"slug":"actor-transformers-for-group-activity","title":"Actor-Transformers for Group Activity Recognition","date":"2020-03-28","arxiv_id":"2003.12737","n_code_links":0,"syntology":null},{"paper":"/paper/variational-transformers-for-diverse-response","slug":"variational-transformers-for-diverse-response","title":"Variational Transformers for Diverse Response Generation","date":"2020-03-28","arxiv_id":"2003.12738","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zlinao/Variational-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"strokecoder-path-based-image-generation-from","title":"StrokeCoder: Path-Based Image Generation from Single Examples using Transformers","date":"2020-03-26","arxiv_id":"2003.11958","n_code_links":0,"syntology":null},{"paper":"/paper/tldr-token-loss-dynamic-reweighting-for","slug":"tldr-token-loss-dynamic-reweighting-for","title":"TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation","date":"2020-03-26","arxiv_id":"2003.11963","n_code_links":1,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ShaojieJiang/tldr"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalizing-spatial-transformers-to","slug":"generalizing-spatial-transformers-to","title":"Generalizing Spatial Transformers to Projective Geometry with Applications to 2D/3D Registration","date":"2020-03-24","arxiv_id":"2003.10987","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-word-translation-of-transformer","title":"Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers","date":"2020-03-21","arxiv_id":"2003.09586","n_code_links":0,"syntology":null},{"paper":"/paper/tnt-kid-transformer-based-neural-tagger-for","slug":"tnt-kid-transformer-based-neural-tagger-for","title":"TNT-KID: Transformer-based Neural Tagger for Keyword Identification","date":"2020-03-20","arxiv_id":"2003.09166","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-lane-and-road-markings-at-a","title":"Detecting Lane and Road Markings at A Distance with Perspective Transformer Layers","date":"2020-03-19","arxiv_id":"2003.08550","n_code_links":0,"syntology":null},{"paper":null,"slug":"normalized-and-geometry-aware-self-attention","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","date":"2020-03-19","arxiv_id":"2003.08897","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-embeddings-and-transformer-models","title":"Temporal Embeddings and Transformer Models for Narrative Text Understanding","date":"2020-03-19","arxiv_id":"2003.08811","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-text-recognition-via-transformer","title":"Scene Text Recognition via Transformer","date":"2020-03-18","arxiv_id":"2003.08077","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-networks-for-trajectory","slug":"transformer-networks-for-trajectory","title":"Transformer Networks for Trajectory Forecasting","date":"2020-03-18","arxiv_id":"2003.08111","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":["FGiuliari/Trajectory-Transformer"],"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/human-activity-recognition-from-wearable","slug":"human-activity-recognition-from-wearable","title":"Human Activity Recognition from Wearable Sensor Data Using Self-Attention","date":"2020-03-17","arxiv_id":"2003.09018","n_code_links":2,"syntology":null},{"paper":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","n_code_links":4,"syntology":null},{"paper":"/paper/rethinking-batch-normalization-in","slug":"rethinking-batch-normalization-in","title":"PowerNorm: Rethinking Batch Normalization in Transformers","date":"2020-03-17","arxiv_id":"2003.07845","n_code_links":1,"syntology":null},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","slug":"trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","arxiv_id":"2003.07000","n_code_links":0,"syntology":null},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","slug":"document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","n_code_links":2,"syntology":null},{"paper":"/paper/learning-to-encode-position-for-transformer","slug":"learning-to-encode-position-for-transformer","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","date":"2020-03-13","arxiv_id":"2003.09229","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":null}},{"paper":"/paper/keyword-attentive-deep-semantic-matching","slug":"keyword-attentive-deep-semantic-matching","title":"Keyword-Attentive Deep Semantic Matching","date":"2020-03-11","arxiv_id":"2003.11516","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-attention-based-transformer-block","title":"Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction","date":"2020-03-10","arxiv_id":"2003.11518","n_code_links":0,"syntology":null},{"paper":"/paper/rezero-is-all-you-need-fast-convergence-at","slug":"rezero-is-all-you-need-fast-convergence-at","title":"ReZero is All You Need: Fast Convergence at Large Depth","date":"2020-03-10","arxiv_id":"2003.04887","n_code_links":13,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["majumderb/rezero"],"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/capacity-of-continuous-channels-with-memory","slug":"capacity-of-continuous-channels-with-memory","title":"Capacity of Continuous Channels with Memory via Directed Information Neural Estimator","date":"2020-03-09","arxiv_id":"2003.04179","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":null,"slug":"cross-modal-learning-for-multi-modal-video","title":"Cross-modal Learning for Multi-modal Video Categorization","date":"2020-03-07","arxiv_id":"2003.03501","n_code_links":0,"syntology":null},{"paper":null,"slug":"ttpp-temporal-transformer-with-progressive","title":"TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation","date":"2020-03-07","arxiv_id":"2003.03530","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-temporal-logics-to-neural-networks","slug":"teaching-temporal-logics-to-neural-networks","title":"Teaching Temporal Logics to Neural Networks","date":"2020-03-06","arxiv_id":"2003.04218","n_code_links":2,"syntology":{"ran":14,"of":24,"n_ran_checked":11,"n_instrument":3,"unverified":10,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["reactive-systems/deepltl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/augmented-transformer-achieves-97-and-85-for","slug":"augmented-transformer-achieves-97-and-85-for","title":"State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesis","date":"2020-03-05","arxiv_id":"2003.02804","n_code_links":1,"syntology":null},{"paper":"/paper/emptransfo-a-multi-head-transformer","slug":"emptransfo-a-multi-head-transformer","title":"EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems","date":"2020-03-05","arxiv_id":"2003.02958","n_code_links":1,"syntology":null},{"paper":"/paper/aligntts-efficient-feed-forward-text-to","slug":"aligntts-efficient-feed-forward-text-to","title":"AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment","date":"2020-03-04","arxiv_id":"2003.01950","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/data-augmentation-using-pre-trained","slug":"data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","date":"2020-03-04","arxiv_id":"2003.02245","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["varinf/TransformersDataAugmentation"],"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":"controllable-time-delay-transformer-for-real","title":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","date":"2020-03-03","arxiv_id":"2003.01309","n_code_links":0,"syntology":null},{"paper":"/paper/heterogeneous-graph-transformer","slug":"heterogeneous-graph-transformer","title":"Heterogeneous Graph Transformer","date":"2020-03-03","arxiv_id":"2003.01332","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":3,"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) · 4 unverified","official":{"repos":["acbull/pyHGT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"meta-embeddings-based-on-self-attention","title":"Meta-Embeddings Based On Self-Attention","date":"2020-03-03","arxiv_id":"2003.01371","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-for-context-aware-spoken","title":"Transfer Learning for Context-Aware Spoken Language Understanding","date":"2020-03-03","arxiv_id":"2003.01305","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer","title":"Transformer++","date":"2020-03-02","arxiv_id":"2003.04974","n_code_links":0,"syntology":null},{"paper":"/paper/unblind-your-apps-predicting-natural-language","slug":"unblind-your-apps-predicting-natural-language","title":"Unblind Your Apps: Predicting Natural-Language Labels for Mobile GUI Components by Deep Learning","date":"2020-03-01","arxiv_id":"2003.00380","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":{"repos":["chenjshnn/LabelDroid"],"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/automatic-perturbation-analysis-on-general","slug":"automatic-perturbation-analysis-on-general","title":"Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond","date":"2020-02-28","arxiv_id":"2002.12920","n_code_links":7,"syntology":{"ran":14,"of":18,"n_ran_checked":13,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["KaidiXu/auto_LiRPA"],"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":"exploring-and-distilling-cross-modal","title":"Exploring and Distilling Cross-Modal Information for Image Captioning","date":"2020-02-28","arxiv_id":"2002.12585","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":"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":"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/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":"/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":"/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/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":"/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":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":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":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}],"record_sha256":"bc3227b904a712b3d65475d6dc95732b3a46282d0a171bceb8fa12a9e2bc14e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}