{"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/absolute-position-encodings/papers/132","list_of":"/method/absolute-position-encodings","method":"Absolute Position Encodings","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":132,"pages_in_order":140,"rows_per_page":100,"rows":[13101,13200],"of":13942,"counts":{"archive_papers_tagged":13942,"with_a_code_link":6505,"where_syntology_ran_a_sample":2224,"not_listed_spam_title":0,"listed":13942,"listed_where_code_ran":2224,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1897,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1897,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/absolute-position-encodings","prev":"/method/absolute-position-encodings/papers/131","next":"/method/absolute-position-encodings/papers/133","papers":[{"paper":"/paper/deebert-dynamic-early-exiting-for","slug":"deebert-dynamic-early-exiting-for","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","date":"2020-04-27","arxiv_id":"2004.12993","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["castorini/deebert"],"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":["listed","official"]}}},{"paper":null,"slug":"explicitly-modeling-adaptive-depths-for","title":"Faster Depth-Adaptive Transformers","date":"2020-04-27","arxiv_id":"2004.13542","n_code_links":0,"syntology":null},{"paper":"/paper/lexically-constrained-neural-machine","slug":"lexically-constrained-neural-machine","title":"Lexically Constrained Neural Machine Translation with Levenshtein Transformer","date":"2020-04-27","arxiv_id":"2004.12681","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":["raymondhs/constrained-levt"],"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/causal-mediation-analysis-for-interpreting","slug":"causal-mediation-analysis-for-interpreting","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","date":"2020-04-26","arxiv_id":"2004.12265","n_code_links":1,"syntology":null},{"paper":null,"slug":"choppy-cut-transformer-for-ranked-list","title":"Choppy: Cut Transformer For Ranked List Truncation","date":"2020-04-26","arxiv_id":"2004.13012","n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-lvt-and-fre-for-transformer","title":"Experiments with LVT and FRE for Transformer model","date":"2020-04-26","arxiv_id":"2004.12495","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-modeling-units-of-transformer","title":"Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition","date":"2020-04-26","arxiv_id":"2004.13522","n_code_links":0,"syntology":null},{"paper":"/paper/all-word-embeddings-from-one-embedding","slug":"all-word-embeddings-from-one-embedding","title":"All Word Embeddings from One Embedding","date":"2020-04-25","arxiv_id":"2004.12073","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":["takase/alone_seq2seq"],"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":null,"slug":"combining-word-embeddings-and-n-grams-for","title":"Combining Word Embeddings and N-grams for Unsupervised Document Summarization","date":"2020-04-25","arxiv_id":"2004.14119","n_code_links":0,"syntology":null},{"paper":"/paper/flat-chinese-ner-using-flat-lattice","slug":"flat-chinese-ner-using-flat-lattice","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","date":"2020-04-24","arxiv_id":"2004.11795","n_code_links":1,"syntology":null},{"paper":"/paper/lite-transformer-with-long-short-range","slug":"lite-transformer-with-long-short-range","title":"Lite Transformer with Long-Short Range Attention","date":"2020-04-24","arxiv_id":"2004.11886","n_code_links":2,"syntology":null},{"paper":"/paper/on-sparsifying-encoder-outputs-in-sequence-to","slug":"on-sparsifying-encoder-outputs-in-sequence-to","title":"On Sparsifying Encoder Outputs in Sequence-to-Sequence Models","date":"2020-04-24","arxiv_id":"2004.11854","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-when-spatial-transformer","slug":"understanding-when-spatial-transformer","title":"Understanding when spatial transformer networks do not support invariance, and what to do about it","date":"2020-04-24","arxiv_id":"2004.11678","n_code_links":1,"syntology":null},{"paper":"/paper/moltrans-molecular-interaction-transformer","slug":"moltrans-molecular-interaction-transformer","title":"MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction","date":"2020-04-23","arxiv_id":"2004.11424","n_code_links":1,"syntology":null},{"paper":"/paper/self-attention-attribution-interpreting","slug":"self-attention-attribution-interpreting","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","date":"2020-04-23","arxiv_id":"2004.11207","n_code_links":2,"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":["YRdddream/attattr"],"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":null,"slug":"uhh-lt-lt2-at-semeval-2020-task-12-fine","title":"UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection","date":"2020-04-23","arxiv_id":"2004.11493","n_code_links":0,"syntology":null},{"paper":"/paper/logical-natural-language-generation-from-open","slug":"logical-natural-language-generation-from-open","title":"Logical Natural Language Generation from Open-Domain Tables","date":"2020-04-22","arxiv_id":"2004.10404","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["wenhuchen/LogicNLG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-a-competitive-end-to-end-speech","slug":"towards-a-competitive-end-to-end-speech","title":"Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription","date":"2020-04-22","arxiv_id":"2004.10799","n_code_links":1,"syntology":null},{"paper":"/paper/attention-module-is-not-only-a-weight","slug":"attention-module-is-not-only-a-weight","title":"Attention is Not Only a Weight: Analyzing Transformers with Vector Norms","date":"2020-04-21","arxiv_id":"2004.10102","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gorokoba560/norm-analysis-of-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/contextual-neural-machine-translation","slug":"contextual-neural-machine-translation","title":"Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns","date":"2020-04-21","arxiv_id":"2004.09894","n_code_links":1,"syntology":null},{"paper":"/paper/diet-lightweight-language-understanding-for","slug":"diet-lightweight-language-understanding-for","title":"DIET: Lightweight Language Understanding for Dialogue Systems","date":"2020-04-21","arxiv_id":"2004.09936","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["RasaHQ/DIET-paper"],"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/keyphrase-generation-with-cross-document","slug":"keyphrase-generation-with-cross-document","title":"Keyphrase Generation with Cross-Document Attention","date":"2020-04-21","arxiv_id":"2004.09800","n_code_links":1,"syntology":null},{"paper":"/paper/pai-gcn-permutable-anisotropic-graph","slug":"pai-gcn-permutable-anisotropic-graph","title":"Learning Local Neighboring Structure for Robust 3D Shape Representation","date":"2020-04-21","arxiv_id":"2004.09995","n_code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-contrastive-predictive","slug":"vector-quantized-contrastive-predictive","title":"Vector Quantized Contrastive Predictive Coding for Template-based Music Generation","date":"2020-04-21","arxiv_id":"2004.10120","n_code_links":1,"syntology":null},{"paper":null,"slug":"weakly-aligned-joint-cross-modality-super","title":"Single Pair Cross-Modality Super Resolution","date":"2020-04-21","arxiv_id":"2004.09965","n_code_links":0,"syntology":null},{"paper":"/paper/a-review-based-transformer-model-for","slug":"a-review-based-transformer-model-for","title":"Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search","date":"2020-04-20","arxiv_id":"2004.09424","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["kepingbi/ProdSearch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-covid-predicting-covid-19-from-chest-x","slug":"deep-covid-predicting-covid-19-from-chest-x","title":"Deep-COVID: Predicting COVID-19 From Chest X-Ray Images Using Deep Transfer Learning","date":"2020-04-20","arxiv_id":"2004.09363","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-reasoning-network-for-image-text","slug":"transformer-reasoning-network-for-image-text","title":"Transformer Reasoning Network for Image-Text Matching and Retrieval","date":"2020-04-20","arxiv_id":"2004.09144","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mesnico/TERN"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"whaletrans-e2e-whisper-to-natural-speech","title":"End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network","date":"2020-04-20","arxiv_id":"2004.09347","n_code_links":0,"syntology":null},{"paper":"/paper/motion-segmentation-using-frequency-domain","slug":"motion-segmentation-using-frequency-domain","title":"Motion Segmentation using Frequency Domain Transformer Networks","date":"2020-04-18","arxiv_id":"2004.08638","n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-the-transformer-with-linguistic-and","title":"Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation","date":"2020-04-17","arxiv_id":"2004.08053","n_code_links":0,"syntology":null},{"paper":"/paper/etc-encoding-long-and-structured-data-in","slug":"etc-encoding-long-and-structured-data-in","title":"ETC: Encoding Long and Structured Inputs in Transformers","date":"2020-04-17","arxiv_id":"2004.08483","n_code_links":2,"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":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/highway-transformer-self-gating-enhanced-self","slug":"highway-transformer-self-gating-enhanced-self","title":"Highway Transformer: Self-Gating Enhanced Self-Attentive Networks","date":"2020-04-17","arxiv_id":"2004.08178","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["cyk1337/Highway-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/transform-and-tell-entity-aware-news-image","slug":"transform-and-tell-entity-aware-news-image","title":"Transform and Tell: Entity-Aware News Image Captioning","date":"2020-04-17","arxiv_id":"2004.08070","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alasdairtran/transform-and-tell"],"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/understanding-the-difficulty-of-training","slug":"understanding-the-difficulty-of-training","title":"Understanding the Difficulty of Training Transformers","date":"2020-04-17","arxiv_id":"2004.08249","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LiyuanLucasLiu/Transforemr-Clinic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/non-autoregressive-machine-translation-with-1","slug":"non-autoregressive-machine-translation-with-1","title":"Non-Autoregressive Machine Translation with Latent Alignments","date":"2020-04-16","arxiv_id":"2004.07437","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":null}},{"paper":null,"slug":"towards-instance-level-parser-selection-for","title":"Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers","date":"2020-04-16","arxiv_id":"2004.07642","n_code_links":0,"syntology":null},{"paper":"/paper/document-level-representation-learning-using","slug":"document-level-representation-learning-using","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","date":"2020-04-15","arxiv_id":"2004.07180","n_code_links":5,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["allenai/scidocs","allenai/specter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entities-as-experts-sparse-memory-access-with","slug":"entities-as-experts-sparse-memory-access-with","title":"Entities as Experts: Sparse Memory Access with Entity Supervision","date":"2020-04-15","arxiv_id":"2004.07202","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/training-with-quantization-noise-for-extreme","slug":"training-with-quantization-noise-for-extreme","title":"Training with Quantization Noise for Extreme Model Compression","date":"2020-04-15","arxiv_id":"2004.07320","n_code_links":4,"syntology":null},{"paper":"/paper/transformer-based-grapheme-to-phoneme-1","slug":"transformer-based-grapheme-to-phoneme-1","title":"Transformer based Grapheme-to-Phoneme Conversion","date":"2020-04-14","arxiv_id":"2004.06338","n_code_links":1,"syntology":null},{"paper":null,"slug":"proformer-towards-on-device-lsh-projection","title":"ProFormer: Towards On-Device LSH Projection Based Transformers","date":"2020-04-13","arxiv_id":"2004.05801","n_code_links":0,"syntology":null},{"paper":"/paper/public-self-consciousness-for-endowing","slug":"public-self-consciousness-for-endowing","title":"Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness","date":"2020-04-13","arxiv_id":"2004.05816","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skywalker023/pragmatic-consistency"],"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/relation-transformer-network","slug":"relation-transformer-network","title":"Relation Transformer Network","date":"2020-04-13","arxiv_id":"2004.06193","n_code_links":1,"syntology":null},{"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}],"record_sha256":"9ad39a5e80d50c994e6cd4818741a69600dd138ecc7618ffaf98c0a81732cd76","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}