{"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/128","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":128,"pages_in_order":140,"rows_per_page":100,"rows":[12701,12800],"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/127","next":"/method/transformer/papers/129","papers":[{"paper":"/paper/a-simple-approach-for-handling-out-of","slug":"a-simple-approach-for-handling-out-of","title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code","date":"2020-10-23","arxiv_id":"2010.12663","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-framework-for-measuring-the","slug":"deep-learning-framework-for-measuring-the","title":"Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls","date":"2020-10-23","arxiv_id":"2010.12418","n_code_links":1,"syntology":null},{"paper":"/paper/don-t-shoot-butterfly-with-rifles-multi","slug":"don-t-shoot-butterfly-with-rifles-multi","title":"Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer","date":"2020-10-23","arxiv_id":"2010.12180","n_code_links":1,"syntology":null},{"paper":null,"slug":"graphspeech-syntax-aware-graph-attention","title":"GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesis","date":"2020-10-23","arxiv_id":"2010.12423","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-a-high-performance-inference-library","slug":"lightseq-a-high-performance-inference-library","title":"LightSeq: A High Performance Inference Library for Transformers","date":"2020-10-23","arxiv_id":"2010.13887","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-transformer-growth-for-progressive","title":"On the Transformer Growth for Progressive BERT Training","date":"2020-10-23","arxiv_id":"2010.12562","n_code_links":0,"syntology":null},{"paper":null,"slug":"stabilizing-transformer-based-action-sequence","title":"Stabilizing Transformer-Based Action Sequence Generation For Q-Learning","date":"2020-10-23","arxiv_id":"2010.12698","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-end-to-end-speech","slug":"transformer-based-end-to-end-speech","title":"Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention","date":"2020-10-23","arxiv_id":"2010.12155","n_code_links":1,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-transformers-1","slug":"an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","arxiv_id":"2010.11929","n_code_links":158,"syntology":{"ran":307,"of":419,"n_ran_checked":286,"n_instrument":21,"unverified":112,"pointer_only":154,"phrase":"307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified","official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["community","listed","unlocated"]}}},{"paper":null,"slug":"developing-real-time-streaming-transformer","title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","date":"2020-10-22","arxiv_id":"2010.11395","n_code_links":0,"syntology":null},{"paper":"/paper/how-phonotactics-affect-multilingual-and-zero","slug":"how-phonotactics-affect-multilingual-and-zero","title":"How Phonotactics Affect Multilingual and Zero-shot ASR Performance","date":"2020-10-22","arxiv_id":"2010.12104","n_code_links":1,"syntology":null},{"paper":"/paper/n-ode-transformer-a-depth-adaptive-variant-of","slug":"n-ode-transformer-a-depth-adaptive-variant-of","title":"N-ODE Transformer: A Depth-Adaptive Variant of the Transformer Using Neural Ordinary Differential Equations","date":"2020-10-22","arxiv_id":"2010.11358","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-the-source-and-target-contributions","slug":"analyzing-the-source-and-target-contributions","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10907","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-conditioned-dialogue-generation","slug":"generalized-conditioned-dialogue-generation","title":"A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation","date":"2020-10-21","arxiv_id":"2010.11140","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-domain-dialogue-state-tracking-based-on-1","title":"Multi-Domain Dialogue State Tracking based on State Graph","date":"2020-10-21","arxiv_id":"2010.11137","n_code_links":0,"syntology":null},{"paper":"/paper/multi-unit-transformer-for-neural-machine","slug":"multi-unit-transformer-for-neural-machine","title":"Multi-Unit Transformers for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10743","n_code_links":1,"syntology":null},{"paper":null,"slug":"tmt-a-transformer-based-modal-translator-for","title":"TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog","date":"2020-10-21","arxiv_id":"2010.10839","n_code_links":0,"syntology":null},{"paper":"/paper/token-drop-mechanism-for-neural-machine","slug":"token-drop-mechanism-for-neural-machine","title":"Token Drop mechanism for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.11018","n_code_links":1,"syntology":null},{"paper":"/paper/wavetransformer-a-novel-architecture-for","slug":"wavetransformer-a-novel-architecture-for","title":"WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","date":"2020-10-21","arxiv_id":"2010.11098","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2dnn-bert-distillation-with-massive","title":"BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search","date":"2020-10-20","arxiv_id":"2010.10442","n_code_links":0,"syntology":null},{"paper":"/paper/bootleg-chasing-the-tail-with-self-supervised","slug":"bootleg-chasing-the-tail-with-self-supervised","title":"Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation","date":"2020-10-20","arxiv_id":"2010.10363","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["helboukkouri/character-bert"],"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/privacy-preserving-visual-content-tagging","slug":"privacy-preserving-visual-content-tagging","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/privacy-preserving-visual-content-tagging-1","slug":"privacy-preserving-visual-content-tagging-1","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/prop-pre-training-with-representative-words","slug":"prop-pre-training-with-representative-words","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2020-10-20","arxiv_id":"2010.10137","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-scalable-distributed-training-of-deep","title":"Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters","date":"2020-10-20","arxiv_id":"2010.10458","n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-parsing-with-stack","slug":"transition-based-parsing-with-stack","title":"Transition-based Parsing with Stack-Transformers","date":"2020-10-20","arxiv_id":"2010.10669","n_code_links":1,"syntology":null},{"paper":"/paper/infusing-sequential-information-into","slug":"infusing-sequential-information-into","title":"Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism","date":"2020-10-19","arxiv_id":"2010.09194","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-aware-tip-generation-for-vertical","title":"Query-aware Tip Generation for Vertical Search","date":"2020-10-19","arxiv_id":"2010.09254","n_code_links":0,"syntology":null},{"paper":"/paper/saint-integrating-temporal-features-for-ednet","slug":"saint-integrating-temporal-features-for-ednet","title":"SAINT+: Integrating Temporal Features for EdNet Correctness Prediction","date":"2020-10-19","arxiv_id":"2010.12042","n_code_links":4,"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/capturing-longer-context-for-document-level","slug":"capturing-longer-context-for-document-level","title":"Rethinking Document-level Neural Machine Translation","date":"2020-10-18","arxiv_id":"2010.08961","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sunzewei2715/Doc2Doc_NMT"],"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":"cross-lingual-relation-extraction-with","title":"Cross-Lingual Relation Extraction with Transformers","date":"2020-10-16","arxiv_id":"2010.08652","n_code_links":0,"syntology":null},{"paper":null,"slug":"didi-s-machine-translation-system-for-wmt2020","title":"DiDi's Machine Translation System for WMT2020","date":"2020-10-16","arxiv_id":"2010.08185","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-token-level-uncertainty-to-learn","title":"Modeling Token-level Uncertainty to Learn Unknown Concepts in SLU via Calibrated Dirichlet Prior RNN","date":"2020-10-16","arxiv_id":"2010.08101","n_code_links":0,"syntology":null},{"paper":"/paper/towards-natural-bilingual-and-code-switched","slug":"towards-natural-bilingual-and-code-switched","title":"Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion","date":"2020-10-16","arxiv_id":"2010.08136","n_code_links":1,"syntology":null},{"paper":"/paper/compressive-summarization-with-plausibility","slug":"compressive-summarization-with-plausibility","title":"Compressive Summarization with Plausibility and Salience Modeling","date":"2020-10-15","arxiv_id":"2010.07886","n_code_links":1,"syntology":{"ran":15,"of":17,"n_ran_checked":3,"n_instrument":12,"unverified":2,"pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shreydesai/cups"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-guided-bert-for-targeted-aspect-based","slug":"context-guided-bert-for-targeted-aspect-based","title":"Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis","date":"2020-10-15","arxiv_id":"2010.07523","n_code_links":1,"syntology":null},{"paper":null,"slug":"dialoguetrm-exploring-the-intra-and-inter","title":"DialogueTRM: Exploring the Intra- and Inter-Modal Emotional Behaviors in the Conversation","date":"2020-10-15","arxiv_id":"2010.07637","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-study-of-transformers-for-source","slug":"empirical-study-of-transformers-for-source","title":"Empirical Study of Transformers for Source Code","date":"2020-10-15","arxiv_id":"2010.07987","n_code_links":1,"syntology":null},{"paper":"/paper/masked-contrastive-representation-learning","slug":"masked-contrastive-representation-learning","title":"Masked Contrastive Representation Learning for Reinforcement Learning","date":"2020-10-15","arxiv_id":"2010.07470","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["teslacool/m-curl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-task-learning-for-cross-lingual","title":"Multi-Task Learning for Cross-Lingual Abstractive Summarization","date":"2020-10-15","arxiv_id":"2010.07503","n_code_links":0,"syntology":null},{"paper":"/paper/natural-language-rationales-with-full-stack","slug":"natural-language-rationales-with-full-stack","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","date":"2020-10-15","arxiv_id":"2010.07526","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-optical-flow-estimation-in-360","title":"Revisiting Optical Flow Estimation in 360 Videos","date":"2020-10-15","arxiv_id":"2010.08045","n_code_links":0,"syntology":null},{"paper":null,"slug":"da-transformer-distance-aware-transformer","title":"DA-Transformer: Distance-aware Transformer","date":"2020-10-14","arxiv_id":"2010.06925","n_code_links":0,"syntology":null},{"paper":"/paper/length-adaptive-transformer-train-once-with-1","slug":"length-adaptive-transformer-train-once-with-1","title":"Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search","date":"2020-10-14","arxiv_id":"2010.07003","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["clovaai/length-adaptive-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"memformer-the-memory-augmented-transformer-1","title":"Memformer: A Memory-Augmented Transformer for Sequence Modeling","date":"2020-10-14","arxiv_id":"2010.06891","n_code_links":0,"syntology":null},{"paper":"/paper/aspect-based-document-similarity-for-research","slug":"aspect-based-document-similarity-for-research","title":"Aspect-based Document Similarity for Research Papers","date":"2020-10-13","arxiv_id":"2010.06395","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["malteos/aspect-document-similarity"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"context-aware-drive-thru-recommendation","title":"Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants","date":"2020-10-13","arxiv_id":"2010.06197","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-attention-models-with-human","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","date":"2020-10-13","arxiv_id":"2010.06396","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-memory-enhanced-transformer-for-end","slug":"dynamic-memory-enhanced-transformer-for-end","title":"Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems","date":"2020-10-12","arxiv_id":"2010.05740","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-pretrained-language-models-for","title":"Probing Pretrained Language Models for Lexical Semantics","date":"2020-10-12","arxiv_id":"2010.05731","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-translation-of-mathematical-text","title":"Machine Translation of Mathematical Text","date":"2020-10-11","arxiv_id":"2010.05229","n_code_links":0,"syntology":null},{"paper":null,"slug":"information-extraction-from-swedish-medical","title":"Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder","date":"2020-10-10","arxiv_id":"2010.04897","n_code_links":0,"syntology":null},{"paper":"/paper/structured-self-attention-weights-encode","slug":"structured-self-attention-weights-encode","title":"Structured Self-Attention Weights Encode Semantics in Sentiment Analysis","date":"2020-10-10","arxiv_id":"2010.04922","n_code_links":1,"syntology":null},{"paper":"/paper/on-task-level-dialogue-composition-of","slug":"on-task-level-dialogue-composition-of","title":"On Task-Level Dialogue Composition of Generative Transformer Model","date":"2020-10-09","arxiv_id":"2010.04826","n_code_links":1,"syntology":null},{"paper":"/paper/online-back-parsing-for-amr-to-text","slug":"online-back-parsing-for-amr-to-text","title":"Online Back-Parsing for AMR-to-Text Generation","date":"2020-10-09","arxiv_id":"2010.04520","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-nu-voice-conversion-system-for-the-voice","title":"The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders","date":"2020-10-09","arxiv_id":"2010.04446","n_code_links":0,"syntology":null},{"paper":"/paper/a-co-interactive-transformer-for-joint-slot","slug":"a-co-interactive-transformer-for-joint-slot","title":"A Co-Interactive Transformer for Joint Slot Filling and Intent Detection","date":"2020-10-08","arxiv_id":"2010.03880","n_code_links":1,"syntology":null},{"paper":"/paper/deformable-detr-deformable-transformers-for-1","slug":"deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","arxiv_id":"2010.04159","n_code_links":20,"syntology":{"ran":37,"of":55,"n_ran_checked":24,"n_instrument":13,"unverified":18,"pointer_only":21,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 3 violated, 20 with no contract checked; 13 where Syntology's instrument failed) · 18 unverified","official":{"repos":["fundamentalvision/Deformable-DETR"],"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":"improving-attention-mechanism-with-query","title":"Improving Attention Mechanism with Query-Value Interaction","date":"2020-10-08","arxiv_id":"2010.03766","n_code_links":0,"syntology":null},{"paper":"/paper/interlocking-backpropagation-improving","slug":"interlocking-backpropagation-improving","title":"Interlocking Backpropagation: Improving depthwise model-parallelism","date":"2020-10-08","arxiv_id":"2010.04116","n_code_links":1,"syntology":null},{"paper":"/paper/shallow-to-deep-training-for-neural-machine","slug":"shallow-to-deep-training-for-neural-machine","title":"Shallow-to-Deep Training for Neural Machine Translation","date":"2020-10-08","arxiv_id":"2010.03737","n_code_links":1,"syntology":null},{"paper":"/paper/visualnews-a-large-multi-source-news-image","slug":"visualnews-a-large-multi-source-news-image","title":"Visual News: Benchmark and Challenges in News Image Captioning","date":"2020-10-08","arxiv_id":"2010.03743","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-transformers-with-approximate-1","slug":"optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","n_code_links":1,"syntology":null},{"paper":"/paper/super-human-performance-in-online-low-latency","slug":"super-human-performance-in-online-low-latency","title":"Super-Human Performance in Online Low-latency Recognition of Conversational Speech","date":"2020-10-07","arxiv_id":"2010.03449","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-gcrf-recovering-chinese-dropped","slug":"transformer-gcrf-recovering-chinese-dropped","title":"Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields","date":"2020-10-07","arxiv_id":"2010.03224","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-grammatical-error-correction","title":"Adversarial Grammatical Error Correction","date":"2020-10-06","arxiv_id":"2010.02407","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-inference-for-neural-machine","title":"Efficient Inference For Neural Machine Translation","date":"2020-10-06","arxiv_id":"2010.02416","n_code_links":0,"syntology":null},{"paper":null,"slug":"incorporating-behavioral-hypotheses-for-query","title":"Incorporating Behavioral Hypotheses for Query Generation","date":"2020-10-06","arxiv_id":"2010.02667","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-sub-layer-functionalities-of","title":"On the Sub-Layer Functionalities of Transformer Decoder","date":"2020-10-06","arxiv_id":"2010.02648","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-enhanced-neural-model-for-event","title":"Resource-Enhanced Neural Model for Event Argument Extraction","date":"2020-10-06","arxiv_id":"2010.03022","n_code_links":0,"syntology":null},{"paper":null,"slug":"vector-vector-matrix-architecture-a-novel","title":"Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications","date":"2020-10-06","arxiv_id":"2010.08412","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-redundant-mappings-in-transformer","slug":"pruning-redundant-mappings-in-transformer","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","date":"2020-10-05","arxiv_id":"2010.01791","n_code_links":1,"syntology":null},{"paper":null,"slug":"pum-at-semeval-2020-task-12-aggregation-of","title":"PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition","date":"2020-10-05","arxiv_id":"2010.01897","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-neural-text-generation-with","slug":"transformer-based-neural-text-generation-with","title":"Transformer-Based Neural Text Generation with Syntactic Guidance","date":"2020-10-05","arxiv_id":"2010.01737","n_code_links":1,"syntology":null},{"paper":"/paper/tell-me-how-to-ask-again-question-data","slug":"tell-me-how-to-ask-again-question-data","title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","date":"2020-10-04","arxiv_id":"2010.01475","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-chemical-1d-knowledge-using","title":"Beyond Chemical 1D knowledge using Transformers","date":"2020-10-02","arxiv_id":"2010.01027","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-transfer-approaches-to-improve-seq-to","title":"Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesis","date":"2020-10-02","arxiv_id":"2010.00792","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-compare-aggregate-transformer-for","title":"A Compare Aggregate Transformer for Understanding Document-grounded Dialogue","date":"2020-10-01","arxiv_id":"2010.00190","n_code_links":0,"syntology":null},{"paper":"/paper/colake-contextualized-language-and-knowledge","slug":"colake-contextualized-language-and-knowledge","title":"CoLAKE: Contextualized Language and Knowledge Embedding","date":"2020-10-01","arxiv_id":"2010.00309","n_code_links":1,"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":["txsun1997/CoLAKE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":"/paper/phonemer-at-wnut-2020-task-2-sequence","slug":"phonemer-at-wnut-2020-task-2-sequence","title":"Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting","date":"2020-10-01","arxiv_id":"2010.00294","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural-1","slug":"transformers-state-of-the-art-natural-1","title":"Transformers: State-of-the-Art Natural Language Processing","date":"2020-10-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for","title":"WeChat Neural Machine Translation Systems for WMT20","date":"2020-10-01","arxiv_id":"2010.00247","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-hard-retrieval-cross-attention-for","title":"Learning Hard Retrieval Decoder Attention for Transformers","date":"2020-09-30","arxiv_id":"2009.14658","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-systematic-generalization-in-neural","slug":"measuring-systematic-generalization-in-neural","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","date":"2020-09-30","arxiv_id":"2009.14786","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NicolasAG/SGinPG"],"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":"mqtransformer-multi-horizon-forecasts-with","title":"MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention","date":"2020-09-30","arxiv_id":"2009.14799","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-attention-with-performers","slug":"rethinking-attention-with-performers","title":"Rethinking Attention with Performers","date":"2020-09-30","arxiv_id":"2009.14794","n_code_links":7,"syntology":{"ran":11,"of":16,"n_ran_checked":7,"n_instrument":4,"unverified":5,"pointer_only":6,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-simple-but-tough-to-beat-data-augmentation","slug":"a-simple-but-tough-to-beat-data-augmentation","title":"A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation","date":"2020-09-29","arxiv_id":"2009.13818","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":["dinghanshen/Cutoff"],"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":"attention-that-does-not-explain-away","title":"Attention that does not Explain Away","date":"2020-09-29","arxiv_id":"2009.14308","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-prediction-using-limited-twitter-data","title":"Gender prediction using limited Twitter Data","date":"2020-09-29","arxiv_id":"2010.02005","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-learning-for-indonesian","slug":"sequence-to-sequence-learning-for-indonesian","title":"Sequence-to-Sequence Learning for Indonesian Automatic Question Generator","date":"2020-09-29","arxiv_id":"2009.13889","n_code_links":1,"syntology":null},{"paper":"/paper/deep-transformers-with-latent-depth","slug":"deep-transformers-with-latent-depth","title":"Deep Transformers with Latent Depth","date":"2020-09-28","arxiv_id":"2009.13102","n_code_links":1,"syntology":null},{"paper":"/paper/vivo-surpassing-human-performance-in-novel","slug":"vivo-surpassing-human-performance-in-novel","title":"VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning","date":"2020-09-28","arxiv_id":"2009.13682","n_code_links":0,"syntology":null},{"paper":"/paper/a-little-goes-a-long-way-improving-toxic","slug":"a-little-goes-a-long-way-improving-toxic","title":"A little goes a long way: Improving toxic language classification despite data scarcity","date":"2020-09-25","arxiv_id":"2009.12344","n_code_links":1,"syntology":null},{"paper":null,"slug":"hamming-ocr-a-locality-sensitive-hashing","title":"Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition","date":"2020-09-23","arxiv_id":"2009.10874","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-pass-transformer-for-machine","title":"Multi-Pass Transformer for Machine Translation","date":"2020-09-23","arxiv_id":"2009.11382","n_code_links":0,"syntology":null},{"paper":"/paper/seq2edits-sequence-transduction-using-span","slug":"seq2edits-sequence-transduction-using-span","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","date":"2020-09-23","arxiv_id":"2009.11136","n_code_links":1,"syntology":null},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","slug":"alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","arxiv_id":"2009.09672","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-acoustic-events-using-convolutional","title":"Detecting Sound Events Using Convolutional Macaron Net With Pseudo Strong Labels","date":"2020-09-21","arxiv_id":"2009.09632","n_code_links":0,"syntology":null}],"record_sha256":"2009c086c5122191aa7bf519e3531a5668e6820b4ac1c0abc18c3b34293bed7f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}