{"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/residual-connection/papers/269","list_of":"/method/residual-connection","method":"Residual Connection","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":269,"pages_in_order":285,"rows_per_page":100,"rows":[26801,26900],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/268","next":"/method/residual-connection/papers/270","papers":[{"paper":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","n_code_links":0,"syntology":null},{"paper":"/paper/monotonic-multihead-attention-1","slug":"monotonic-multihead-attention-1","title":"Monotonic Multihead Attention","date":"2019-09-26","arxiv_id":"1909.12406","n_code_links":3,"syntology":null},{"paper":"/paper/unsupervised-universal-self-attention-network","slug":"unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","date":"2019-09-26","arxiv_id":"1909.11855","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["daiquocnguyen/Graph-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/attention-convolutional-binary-neural-tree","slug":"attention-convolutional-binary-neural-tree","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","date":"2019-09-25","arxiv_id":"1909.11378","n_code_links":2,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":"/paper/high-fidelity-speech-synthesis-with-1","slug":"high-fidelity-speech-synthesis-with-1","title":"High Fidelity Speech Synthesis with Adversarial Networks","date":"2019-09-25","arxiv_id":"1909.11646","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["mbinkowski/DeepSpeechDistances"],"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":"learning-to-detect-opinion-snippet-for-aspect","title":"Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis","date":"2019-09-25","arxiv_id":"1909.11297","n_code_links":0,"syntology":null},{"paper":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","n_code_links":2,"syntology":null},{"paper":null,"slug":"optimal-transport-cyclegan-and-penalized-ls","title":"Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems","date":"2019-09-25","arxiv_id":"1909.12116","n_code_links":0,"syntology":null},{"paper":null,"slug":"pydens-a-python-framework-for-solving","title":"PyDEns: a Python Framework for Solving Differential Equations with Neural Networks","date":"2019-09-25","arxiv_id":"1909.11544","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","n_code_links":5,"syntology":null},{"paper":null,"slug":"residual-networks-behave-like-boosting","title":"Residual Networks Behave Like Boosting Algorithms","date":"2019-09-25","arxiv_id":"1909.11790","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-recognition-with-augmented-synthesized","title":"Speech Recognition with Augmented Synthesized Speech","date":"2019-09-25","arxiv_id":"1909.11699","n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-accurate-convolutional-object","slug":"fast-and-accurate-convolutional-object","title":"Development of Fast Refinement Detectors on AI Edge Platforms","date":"2019-09-24","arxiv_id":"1909.10798","n_code_links":2,"syntology":null},{"paper":"/paper/knowledge-enriched-transformer-for-emotion","slug":"knowledge-enriched-transformer-for-emotion","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","date":"2019-09-24","arxiv_id":"1909.10681","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhongpeixiang/KET"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/object-contextual-representations-for","slug":"object-contextual-representations-for","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","date":"2019-09-24","arxiv_id":"1909.11065","n_code_links":11,"syntology":{"ran":5,"of":9,"n_ran_checked":1,"n_instrument":4,"unverified":4,"pointer_only":1,"phrase":"5 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; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"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":["listed","official"]}}},{"paper":"/paper/subsampling-generative-adversarial-networks","slug":"subsampling-generative-adversarial-networks","title":"Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss","date":"2019-09-24","arxiv_id":"1909.10670","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["UBCDingXin/DDRE_Sampling_GANs"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"technical-report-on-conversational-question","title":"Technical report on Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10772","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-across-languages-from","title":"Efficiently Reusing Old Models Across Languages via Transfer Learning","date":"2019-09-24","arxiv_id":"1909.10955","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","n_code_links":0,"syntology":null},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/190910430","slug":"190910430","title":"Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings","date":"2019-09-23","arxiv_id":"1909.10430","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-identification-and-normalisation-of","slug":"automatic-identification-and-normalisation-of","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/portuguese-named-entity-recognition-using-1","slug":"portuguese-named-entity-recognition-using-1","title":"Portuguese Named Entity Recognition using BERT-CRF","date":"2019-09-23","arxiv_id":"1909.10649","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":{"repos":["neuralmind-ai/portuguese-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"190909779","title":"Self-attention based end-to-end Hindi-English Neural Machine Translation","date":"2019-09-21","arxiv_id":"1909.09779","n_code_links":0,"syntology":null},{"paper":null,"slug":"190909801","title":"Adversarial Learning of General Transformations for Data Augmentation","date":"2019-09-21","arxiv_id":"1909.09801","n_code_links":0,"syntology":null},{"paper":"/paper/190909725","slug":"190909725","title":"Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation","date":"2019-09-20","arxiv_id":"1909.09725","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","n_code_links":0,"syntology":null},{"paper":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-variational-neural-machine","title":"Improved Variational Neural Machine Translation by Promoting Mutual Information","date":"2019-09-19","arxiv_id":"1909.09237","n_code_links":0,"syntology":null},{"paper":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","n_code_links":0,"syntology":null},{"paper":"/paper/timage-a-robust-time-series-classification","slug":"timage-a-robust-time-series-classification","title":"Timage -- A Robust Time Series Classification Pipeline","date":"2019-09-19","arxiv_id":"1909.09149","n_code_links":1,"syntology":null},{"paper":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","n_code_links":1,"syntology":null},{"paper":"/paper/extremely-weak-supervised-image-to-image","slug":"extremely-weak-supervised-image-to-image","title":"Extremely Weak Supervised Image-to-Image Translation for Semantic Segmentation","date":"2019-09-18","arxiv_id":"1909.08542","n_code_links":1,"syntology":null},{"paper":"/paper/improving-natural-language-inference-with-a","slug":"improving-natural-language-inference-with-a","title":"Improving Natural Language Inference with a Pretrained Parser","date":"2019-09-18","arxiv_id":"1909.08217","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-bert-for-word-sense-disambiguation","title":"Using BERT for Word Sense Disambiguation","date":"2019-09-18","arxiv_id":"1909.08358","n_code_links":0,"syntology":null},{"paper":"/paper/adaptis-adaptive-instance-selection-network","slug":"adaptis-adaptive-instance-selection-network","title":"AdaptIS: Adaptive Instance Selection Network","date":"2019-09-17","arxiv_id":"1909.07829","n_code_links":0,"syntology":null},{"paper":"/paper/do-nlp-models-know-numbers-probing-numeracy","slug":"do-nlp-models-know-numbers-probing-numeracy","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","date":"2019-09-17","arxiv_id":"1909.07940","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-evidence-of-supplement-drug","slug":"extracting-evidence-of-supplement-drug","title":"SUPP.AI: Finding Evidence for Supplement-Drug Interactions","date":"2019-09-17","arxiv_id":"1909.08135","n_code_links":1,"syntology":null},{"paper":"/paper/k-bert-enabling-language-representation-with","slug":"k-bert-enabling-language-representation-with","title":"K-BERT: Enabling Language Representation with Knowledge Graph","date":"2019-09-17","arxiv_id":"1909.07606","n_code_links":2,"syntology":null},{"paper":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","n_code_links":10,"syntology":{"ran":12,"of":47,"n_ran_checked":7,"n_instrument":5,"unverified":35,"pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"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":"simple-yet-effective-bridge-reasoning-for","title":"Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering","date":"2019-09-17","arxiv_id":"1909.07597","n_code_links":0,"syntology":null},{"paper":"/paper/span-based-joint-entity-and-relation","slug":"span-based-joint-entity-and-relation","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","date":"2019-09-17","arxiv_id":"1909.07755","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-self-attentional-neural-architecture-for","title":"A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning","date":"2019-09-16","arxiv_id":"1909.06983","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-neural-models-for-sequence-modelling","title":"Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds","date":"2019-09-16","arxiv_id":"1909.07102","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-neural-machine-translation-for","slug":"multilingual-neural-machine-translation-for","title":"Multilingual Neural Machine Translation for Zero-Resource Languages","date":"2019-09-16","arxiv_id":"1909.07342","n_code_links":1,"syntology":null},{"paper":"/paper/probing-natural-language-inference-models","slug":"probing-natural-language-inference-models","title":"Probing Natural Language Inference Models through Semantic Fragments","date":"2019-09-16","arxiv_id":"1909.07521","n_code_links":3,"syntology":null},{"paper":"/paper/automatically-extracting-challenge-sets-for","slug":"automatically-extracting-challenge-sets-for","title":"Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation","date":"2019-09-15","arxiv_id":"1909.06814","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-mad-a-novel-interpretable-malware-detector","title":"I-MAD: Interpretable Malware Detector Using Galaxy Transformer","date":"2019-09-15","arxiv_id":"1909.06865","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-and-power-evaluation-of-ai","title":"Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training","date":"2019-09-15","arxiv_id":"1909.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-09-14","arxiv_id":"1909.06618","n_code_links":0,"syntology":null},{"paper":"/paper/ouroboros-on-accelerating-training-of","slug":"ouroboros-on-accelerating-training-of","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models","date":"2019-09-14","arxiv_id":"1909.06695","n_code_links":1,"syntology":null},{"paper":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["yaushian/Tree-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","n_code_links":2,"syntology":null},{"paper":"/paper/addressing-semantic-drift-in-question","slug":"addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","arxiv_id":"1909.06356","n_code_links":2,"syntology":{"ran":13,"of":19,"n_ran_checked":11,"n_instrument":2,"unverified":6,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ZhangShiyue/QGforQA"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"defending-against-adversarial-attacks-by-3","title":"Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix","date":"2019-09-13","arxiv_id":"1909.06137","n_code_links":0,"syntology":null},{"paper":"/paper/dual-graph-convolutional-network-for-semantic","slug":"dual-graph-convolutional-network-for-semantic","title":"Dual Graph Convolutional Network for Semantic Segmentation","date":"2019-09-13","arxiv_id":"1909.06121","n_code_links":6,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-4-bit","title":"Neural Machine Translation with 4-Bit Precision and Beyond","date":"2019-09-13","arxiv_id":"1909.06091","n_code_links":0,"syntology":null},{"paper":null,"slug":"sanvis-visual-analytics-for-understanding","title":"SANVis: Visual Analytics for Understanding Self-Attention Networks","date":"2019-09-13","arxiv_id":"1909.09595","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-graph-parsing-by-attention-graph","title":"Scene Graph Parsing by Attention Graph","date":"2019-09-13","arxiv_id":"1909.06273","n_code_links":0,"syntology":null},{"paper":"/paper/towards-open-domain-named-entity-recognition","slug":"towards-open-domain-named-entity-recognition","title":"Neural Correction Model for Open-Domain Named Entity Recognition","date":"2019-09-13","arxiv_id":"1909.06058","n_code_links":1,"syntology":null},{"paper":null,"slug":"cuni-system-for-the-building-educational-1","title":"CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction","date":"2019-09-12","arxiv_id":"1909.05553","n_code_links":0,"syntology":null},{"paper":"/paper/diffgrad-an-optimization-method-for","slug":"diffgrad-an-optimization-method-for","title":"diffGrad: An Optimization Method for Convolutional Neural Networks","date":"2019-09-12","arxiv_id":"1909.11015","n_code_links":1,"syntology":null},{"paper":"/paper/gresnet-graph-residuals-for-reviving-deep","slug":"gresnet-graph-residuals-for-reviving-deep","title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","date":"2019-09-12","arxiv_id":"1909.05729","n_code_links":2,"syntology":null},{"paper":null,"slug":"measuring-domain-portability-and","title":"Measuring Domain Portability and ErrorPropagation in Biomedical QA","date":"2019-09-12","arxiv_id":"1909.09704","n_code_links":0,"syntology":null},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","n_code_links":0,"syntology":null},{"paper":"/paper/uer-an-open-source-toolkit-for-pre-training","slug":"uer-an-open-source-toolkit-for-pre-training","title":"UER: An Open-Source Toolkit for Pre-training Models","date":"2019-09-12","arxiv_id":"1909.05658","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dbiir/UER-py"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertgrid-contextualized-embedding-for-2d","slug":"bertgrid-contextualized-embedding-for-2d","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","date":"2019-09-11","arxiv_id":"1909.04948","n_code_links":2,"syntology":null},{"paper":"/paper/ctrl-a-conditional-transformer-language-model-1","slug":"ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","arxiv_id":"1909.05858","n_code_links":8,"syntology":{"ran":14,"of":14,"n_ran_checked":11,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"dnanet-de-normalized-attention-based-multi","title":"Learning Enhanced Resolution-wise features for Human Pose Estimation","date":"2019-09-11","arxiv_id":"1909.05090","n_code_links":0,"syntology":null},{"paper":"/paper/from-english-to-code-switching-transfer","slug":"from-english-to-code-switching-transfer","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","date":"2019-09-11","arxiv_id":"1909.05158","n_code_links":1,"syntology":null},{"paper":"/paper/frustratingly-easy-natural-question-answering","slug":"frustratingly-easy-natural-question-answering","title":"Frustratingly Easy Natural Question Answering","date":"2019-09-11","arxiv_id":"1909.05286","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-locality-in-event-extraction","title":"Global Locality in Biomedical Relation and Event Extraction","date":"2019-09-11","arxiv_id":"1909.04822","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-bert-answer-questions-a-layer-wise","slug":"how-does-bert-answer-questions-a-layer-wise","title":"How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations","date":"2019-09-11","arxiv_id":"1909.04925","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["bvanaken/explain-BERT-QA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-understanding-the-importance-of","title":"Towards Understanding the Importance of Shortcut Connections in Residual Networks","date":"2019-09-10","arxiv_id":"1909.04653","n_code_links":0,"syntology":null},{"paper":null,"slug":"vacl-variance-aware-cross-layer","title":"VACL: Variance-Aware Cross-Layer Regularization for Pruning Deep Residual Networks","date":"2019-09-10","arxiv_id":"1909.04485","n_code_links":0,"syntology":null},{"paper":"/paper/video-representation-learning-by-dense","slug":"video-representation-learning-by-dense","title":"Video Representation Learning by Dense Predictive Coding","date":"2019-09-10","arxiv_id":"1909.04656","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["TengdaHan/DPC"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/when-single-event-upset-meets-deep-neural","slug":"when-single-event-upset-meets-deep-neural","title":"When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remedies","date":"2019-09-10","arxiv_id":"1909.04697","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-arabic-social-media","title":"BERT-Based Arabic Social Media Author Profiling","date":"2019-09-09","arxiv_id":"1909.04181","n_code_links":0,"syntology":null},{"paper":"/paper/cbnet-a-novel-composite-backbone-network","slug":"cbnet-a-novel-composite-backbone-network","title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","date":"2019-09-09","arxiv_id":"1909.03625","n_code_links":6,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":1,"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":["PKUbahuangliuhe/CBNet"],"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":"forecaster-a-graph-transformer-for","title":"Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data","date":"2019-09-09","arxiv_id":"1909.04019","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-enhanced-contextual-word","slug":"knowledge-enhanced-contextual-word","title":"Knowledge Enhanced Contextual Word Representations","date":"2019-09-09","arxiv_id":"1909.04164","n_code_links":1,"syntology":null},{"paper":"/paper/lcscnet-linear-compressing-based-skip","slug":"lcscnet-linear-compressing-based-skip","title":"LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution","date":"2019-09-09","arxiv_id":"1909.03573","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-a-self-inverse-network-for-unpaired","title":"One-to-one Mapping for Unpaired Image-to-image Translation","date":"2019-09-09","arxiv_id":"1909.04110","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-language-models-for-sequential","slug":"pretrained-language-models-for-sequential","title":"Pretrained Language Models for Sequential Sentence Classification","date":"2019-09-09","arxiv_id":"1909.04054","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","slug":"reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","arxiv_id":"1909.03745","n_code_links":0,"syntology":null},{"paper":"/paper/span-selection-pre-training-for-question","slug":"span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","date":"2019-09-09","arxiv_id":"1909.04120","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["IBM/span-selection-pretraining"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"commonsense-knowledge-bert-for-level-2","title":"Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test","date":"2019-09-08","arxiv_id":"1909.03415","n_code_links":0,"syntology":null},{"paper":null,"slug":"czech-text-processing-with-contextual","title":"Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER","date":"2019-09-08","arxiv_id":"1909.03544","n_code_links":0,"syntology":null},{"paper":"/paper/entity-relation-and-event-extraction-with","slug":"entity-relation-and-event-extraction-with","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","date":"2019-09-08","arxiv_id":"1909.03546","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["dwadden/dygiepp"],"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":"multi-task-bidirectional-transformer","title":"Multi-Task Bidirectional Transformer Representations for Irony Detection","date":"2019-09-08","arxiv_id":"1909.03526","n_code_links":0,"syntology":null},{"paper":"/paper/symmetric-regularization-based-bert-for-pair","slug":"symmetric-regularization-based-bert-for-pair","title":"Symmetric Regularization based BERT for Pair-wise Semantic Reasoning","date":"2019-09-08","arxiv_id":"1909.03405","n_code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-robustness-in-multi-class","slug":"transfer-learning-robustness-in-multi-class","title":"Transfer Learning Robustness in Multi-Class Categorization by Fine-Tuning Pre-Trained Contextualized Language Models","date":"2019-09-08","arxiv_id":"1909.03564","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-hierarchical-binary-tagging-framework","slug":"a-novel-hierarchical-binary-tagging-framework","title":"A Novel Cascade Binary Tagging Framework for Relational Triple Extraction","date":"2019-09-07","arxiv_id":"1909.03227","n_code_links":5,"syntology":null},{"paper":"/paper/kg-bert-bert-for-knowledge-graph-completion","slug":"kg-bert-bert-for-knowledge-graph-completion","title":"KG-BERT: BERT for Knowledge Graph Completion","date":"2019-09-07","arxiv_id":"1909.03193","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yao8839836/kg-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-extractive-and-abstractive-neural-document","slug":"on-extractive-and-abstractive-neural-document","title":"On Extractive and Abstractive Neural Document Summarization with Transformer Language Models","date":"2019-09-07","arxiv_id":"1909.03186","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":null}}],"record_sha256":"b3e0a088bbe10b3dea730fef58e09070e197b9790647ca0f88d2b740e809b791","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}