{"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/241","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":241,"pages_in_order":285,"rows_per_page":100,"rows":[24001,24100],"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/240","next":"/method/residual-connection/papers/242","papers":[{"paper":null,"slug":"a-structure-enhanced-graph-convolutional","title":"A structure-enhanced graph convolutional network for sentiment analysis","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-approaches-to-enhancing","title":"Active Learning Approaches to Enhancing Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/approximation-of-response-knowledge-retrieval","slug":"approximation-of-response-knowledge-retrieval","title":"Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/chime-cross-passage-hierarchical-memory","slug":"chime-cross-passage-hierarchical-memory","title":"CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering","date":"2020-11-01","arxiv_id":"2011.00519","n_code_links":1,"syntology":null},{"paper":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"context-analysis-for-pre-trained-masked","title":"Context Analysis for Pre-trained Masked Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","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":["gingsi/coot-videotext"],"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":"cross-lingual-training-of-neural-models-for","title":"Cross-Lingual Training of Neural Models for Document Ranking","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/decoding-language-spatial-relations-to-2d","slug":"decoding-language-spatial-relations-to-2d","title":"Decoding Language Spatial Relations to 2D Spatial Arrangements","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamically-throttleable-neural-networks-tnn","title":"Dynamically Throttleable Neural Networks (TNN)","date":"2020-11-01","arxiv_id":"2011.02836","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-generalization-in-natural-language","slug":"enhancing-generalization-in-natural-language","title":"Enhancing Generalization in Natural Language Inference by Syntax","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exbert-extending-pre-trained-models-with","title":"exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-transformer-for-multi-domain","title":"Factorized Transformer for Multi-Domain Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-language-detection","title":"Hate-Speech and Offensive Language Detection in Roman Urdu","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"huji-ku-at-mrp-2020-two-transition-based-1","title":"HUJI-KU at MRP 2020: Two Transition-based Neural Parsers","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/integrating-task-specific-information-into","slug":"integrating-task-specific-information-into","title":"Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"investigation-of-bert-model-on-biomedical","title":"Investigation of BERT Model on Biomedical Relation Extraction Based on Revised Fine-tuning Mechanism","date":"2020-11-01","arxiv_id":"2011.00398","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-ground-medical-text-in-a-3d-human","slug":"learning-to-ground-medical-text-in-a-3d-human","title":"Learning to ground medical text in a 3D human atlas","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/limit-bert-linguistics-informed-multi-task","slug":"limit-bert-linguistics-informed-multi-task","title":"LIMIT-BERT : Linguistics Informed Multi-Task BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"making-information-seeking-easier-an-improved","title":"Making Information Seeking Easier: An Improved Pipeline for Conversational Search","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-intra-and-inter-modality-incongruity","title":"Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information-1","slug":"multi-2oie-multilingual-open-information-1","title":"Multi\\^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-word-segmentation-for-downstream","slug":"optimizing-word-segmentation-for-downstream","title":"Optimizing Word Segmentation for Downstream Task","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-responses-to-psychological","title":"Predicting Responses to Psychological Questionnaires from Participants' Social Media Posts and Question Text Embeddings","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-type-driven","slug":"representation-learning-for-type-driven","title":"Representation Learning for Type-Driven Composition","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"smrt-chatbots-improving-non-task-oriented","title":"SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training","date":"2020-11-01","arxiv_id":"2011.00547","n_code_links":0,"syntology":null},{"paper":"/paper/social-chemistry-101-learning-to-reason-about","slug":"social-chemistry-101-learning-to-reason-about","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","date":"2020-11-01","arxiv_id":"2011.00620","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-amazing-world-of-neural-language","title":"The Amazing World of Neural Language Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-relx-dataset-and-matching-the-1","slug":"the-relx-dataset-and-matching-the-1","title":"The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/towards-zero-shot-conditional-summarization","slug":"towards-zero-shot-conditional-summarization","title":"Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-multi-aspect-modeling-for","title":"Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis","date":"2020-11-01","arxiv_id":"2011.00476","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision-1","slug":"visually-grounded-planning-without-vision-1","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/free-the-plural-unrestricted-split-antecedent","slug":"free-the-plural-unrestricted-split-antecedent","title":"Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution","date":"2020-10-31","arxiv_id":"2011.00245","n_code_links":1,"syntology":null},{"paper":null,"slug":"methods-for-pruning-deep-neural-networks","title":"Methods for Pruning Deep Neural Networks","date":"2020-10-31","arxiv_id":"2011.00241","n_code_links":0,"syntology":null},{"paper":"/paper/neural-coreference-resolution-for-arabic","slug":"neural-coreference-resolution-for-arabic","title":"Neural Coreference Resolution for Arabic","date":"2020-10-31","arxiv_id":"2011.00286","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-xx205-system-for-the-voxceleb-speaker","title":"The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020","date":"2020-10-31","arxiv_id":"2011.00200","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-pre-trained-bert-for-aspect","slug":"understanding-pre-trained-bert-for-aspect","title":"Understanding Pre-trained BERT for Aspect-based Sentiment Analysis","date":"2020-10-31","arxiv_id":"2011.00169","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-sui-generis-qa-approach-using-roberta-for","title":"A Sui Generis QA Approach using RoBERTa for Adverse Drug Event Identification","date":"2020-10-30","arxiv_id":"2011.00057","n_code_links":0,"syntology":null},{"paper":"/paper/generating-radiology-reports-via-memory","slug":"generating-radiology-reports-via-memory","title":"Generating Radiology Reports via Memory-driven Transformer","date":"2020-10-30","arxiv_id":"2010.16056","n_code_links":2,"syntology":{"ran":26,"of":31,"n_ran_checked":20,"n_instrument":6,"unverified":5,"pointer_only":25,"phrase":"26 ran (of which 13 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 3 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhjohnchan/R2Gen"],"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":["found_in_text","listed","official"]}}},{"paper":null,"slug":"improving-dialogue-breakdown-detection-with","title":"Improving Dialogue Breakdown Detection with Semi-Supervised Learning","date":"2020-10-30","arxiv_id":"2011.00136","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-labeling-using-a-deep-contextualized","slug":"semantic-labeling-using-a-deep-contextualized","title":"Semantic Labeling Using a Deep Contextualized Language Model","date":"2020-10-30","arxiv_id":"2010.16037","n_code_links":1,"syntology":null},{"paper":null,"slug":"slm-learning-a-discourse-language","title":"SLM: Learning a Discourse Language Representation with Sentence Unshuffling","date":"2020-10-30","arxiv_id":"2010.16249","n_code_links":0,"syntology":null},{"paper":"/paper/target-word-masking-for-location-metonymy","slug":"target-word-masking-for-location-metonymy","title":"Target Word Masking for Location Metonymy Resolution","date":"2020-10-30","arxiv_id":"2010.16097","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","n_code_links":0,"syntology":null},{"paper":"/paper/veco-variable-encoder-decoder-pre-training-1","slug":"veco-variable-encoder-decoder-pre-training-1","title":"VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation","date":"2020-10-30","arxiv_id":"2010.16046","n_code_links":1,"syntology":null},{"paper":"/paper/combining-self-training-and-self-supervised","slug":"combining-self-training-and-self-supervised","title":"Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection","date":"2020-10-29","arxiv_id":"2010.15360","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-bert-conditioning-the-language","title":"Contextual BERT: Conditioning the Language Model Using a Global State","date":"2020-10-29","arxiv_id":"2010.15778","n_code_links":0,"syntology":null},{"paper":null,"slug":"devicetts-a-small-footprint-fast-stable","title":"DeviceTTS: A Small-Footprint, Fast, Stable Network for On-Device Text-to-Speech","date":"2020-10-29","arxiv_id":"2010.15311","n_code_links":0,"syntology":null},{"paper":"/paper/greedy-optimization-provably-wins-the-lottery","slug":"greedy-optimization-provably-wins-the-lottery","title":"Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough","date":"2020-10-29","arxiv_id":"2010.15969","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-attentive-fusion-external-language","title":"Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model","date":"2020-10-29","arxiv_id":"2010.15437","n_code_links":0,"syntology":null},{"paper":"/paper/relationnet-bridging-visual-representations","slug":"relationnet-bridging-visual-representations","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","date":"2020-10-29","arxiv_id":"2010.15831","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/RelationNet2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tilde-at-wmt-2020-news-task-systems","title":"Tilde at WMT 2020: News Task Systems","date":"2020-10-29","arxiv_id":"2010.15423","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-methods-for-semi-supervised-text","title":"Bayesian Methods for Semi-supervised Text Annotation","date":"2020-10-28","arxiv_id":"2010.14872","n_code_links":0,"syntology":null},{"paper":"/paper/desmog-detecting-stance-in-media-on-global","slug":"desmog-detecting-stance-in-media-on-global","title":"Detecting Stance in Media on Global Warming","date":"2020-10-28","arxiv_id":"2010.15149","n_code_links":1,"syntology":null},{"paper":null,"slug":"fusion-models-for-improved-visual-captioning","title":"Fusion Models for Improved Visual Captioning","date":"2020-10-28","arxiv_id":"2010.15251","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-unknot","title":"Learning to Unknot","date":"2020-10-28","arxiv_id":"2010.16263","n_code_links":0,"syntology":null},{"paper":"/paper/model-rubik-s-cube-twisting-resolution-depth","slug":"model-rubik-s-cube-twisting-resolution-depth","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","date":"2020-10-28","arxiv_id":"2010.14819","n_code_links":9,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/CV-backbones","huawei-noah/ghostnet"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/replay-and-synthetic-speech-detection-with","slug":"replay-and-synthetic-speech-detection-with","title":"Replay and Synthetic Speech Detection with Res2net Architecture","date":"2020-10-28","arxiv_id":"2010.15006","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-volctrans-machine-translation-system-for","title":"The Volctrans Machine Translation System for WMT20","date":"2020-10-28","arxiv_id":"2010.14806","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-clarifying-question-selection-system-from","title":"A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge","date":"2020-10-27","arxiv_id":"2010.14202","n_code_links":0,"syntology":null},{"paper":"/paper/bytecover-cover-song-identification-via-multi","slug":"bytecover-cover-song-identification-via-multi","title":"ByteCover: Cover Song Identification via Multi-Loss Training","date":"2020-10-27","arxiv_id":"2010.14022","n_code_links":1,"syntology":null},{"paper":"/paper/fast-interleaved-bidirectional-sequence","slug":"fast-interleaved-bidirectional-sequence","title":"Fast Interleaved Bidirectional Sequence Generation","date":"2020-10-27","arxiv_id":"2010.14481","n_code_links":1,"syntology":null},{"paper":"/paper/fragmentvc-any-to-any-voice-conversion-by-end","slug":"fragmentvc-any-to-any-voice-conversion-by-end","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","date":"2020-10-27","arxiv_id":"2010.14150","n_code_links":2,"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":["yistLin/FragmentVC"],"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":"know-where-to-drop-your-weights-towards","title":"Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation","date":"2020-10-27","arxiv_id":"2010.14019","n_code_links":0,"syntology":null},{"paper":"/paper/mmft-bert-multimodal-fusion-transformer-with","slug":"mmft-bert-multimodal-fusion-transformer-with","title":"MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering","date":"2020-10-27","arxiv_id":"2010.14095","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-with","slug":"multimodal-emotion-recognition-with","title":"Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature Fusion","date":"2020-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"parallel-waveform-synthesis-based-on","title":"Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators","date":"2020-10-27","arxiv_id":"2010.14151","n_code_links":0,"syntology":null},{"paper":"/paper/speech-simclr-combining-contrastive-and","slug":"speech-simclr-combining-contrastive-and","title":"Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning","date":"2020-10-27","arxiv_id":"2010.13991","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["athena-team/athena"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"to-bert-or-not-to-bert-comparing-task","title":"To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging","date":"2020-10-27","arxiv_id":"2010.14042","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-contextual-stereotypes-measuring","slug":"unmasking-contextual-stereotypes-measuring","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","date":"2020-10-27","arxiv_id":"2010.14534","n_code_links":1,"syntology":null},{"paper":"/paper/accelerating-training-of-transformer-based","slug":"accelerating-training-of-transformer-based","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","date":"2020-10-26","arxiv_id":"2010.13369","n_code_links":1,"syntology":null},{"paper":"/paper/controlled-molecule-generator-for-optimizing","slug":"controlled-molecule-generator-for-optimizing","title":"Controlled Molecule Generator for Optimizing Multiple Chemical Properties","date":"2020-10-26","arxiv_id":"2010.13908","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deargen/cmg"],"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":"/paper/detection-and-segmentation-of-lesion-areas-in","slug":"detection-and-segmentation-of-lesion-areas-in","title":"Detection and Segmentation of Lesion Areas in Chest CT Scans For The Prediction of COVID-19","date":"2020-10-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fastformers-highly-efficient-transformer","slug":"fastformers-highly-efficient-transformer","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","date":"2020-10-26","arxiv_id":"2010.13382","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/fastformers"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fine-grained-information-status-1","slug":"fine-grained-information-status-1","title":"Fine-grained Information Status Classification Using Discourse Context-Aware BERT","date":"2020-10-26","arxiv_id":"2010.14759","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-transformer-networks-with-syntactic-and","title":"Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction","date":"2020-10-26","arxiv_id":"2010.13391","n_code_links":0,"syntology":null},{"paper":null,"slug":"handgun-detection-using-combined-human-pose","title":"Handgun detection using combined human pose and weapon appearance","date":"2020-10-26","arxiv_id":"2010.13753","n_code_links":0,"syntology":null},{"paper":null,"slug":"peak-detection-on-data-independent","title":"Peak Detection On Data Independent Acquisition Mass Spectrometry Data With Semisupervised Convolutional Transformers","date":"2020-10-26","arxiv_id":"2010.13841","n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-the-computational-cost-of-deep-1","title":"Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks","date":"2020-10-26","arxiv_id":"2010.13476","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-spoken-language-understanding","slug":"semi-supervised-spoken-language-understanding","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","date":"2020-10-26","arxiv_id":"2010.13826","n_code_links":1,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2020-task-12-multilingual","title":"UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models","date":"2020-10-26","arxiv_id":"2010.13609","n_code_links":0,"syntology":null},{"paper":"/paper/attention-is-all-you-need-in-speech","slug":"attention-is-all-you-need-in-speech","title":"Attention is All You Need in Speech Separation","date":"2020-10-25","arxiv_id":"2010.13154","n_code_links":4,"syntology":null},{"paper":null,"slug":"commonsense-knowledge-adversarial-dataset","title":"Commonsense knowledge adversarial dataset that challenges ELECTRA","date":"2020-10-25","arxiv_id":"2010.13049","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-word-embeddings-encode-aspects","title":"Contextualized Word Embeddings Encode Aspects of Human-Like Word Sense Knowledge","date":"2020-10-25","arxiv_id":"2010.13057","n_code_links":0,"syntology":null},{"paper":null,"slug":"crab-class-representation-attentive-bert-for","title":"CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media","date":"2020-10-25","arxiv_id":"2010.13028","n_code_links":0,"syntology":null},{"paper":"/paper/two-stage-textual-knowledge-distillation-to","slug":"two-stage-textual-knowledge-distillation-to","title":"Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding","date":"2020-10-25","arxiv_id":"2010.13105","n_code_links":1,"syntology":null},{"paper":null,"slug":"char2subword-extending-the-subword-embedding","title":"Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality","date":"2020-10-24","arxiv_id":"2010.12730","n_code_links":0,"syntology":null},{"paper":"/paper/cough-a-challenge-dataset-and-models-for","slug":"cough-a-challenge-dataset-and-models-for","title":"COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval","date":"2020-10-24","arxiv_id":"2010.12800","n_code_links":1,"syntology":null},{"paper":"/paper/effective-distant-supervision-for-temporal","slug":"effective-distant-supervision-for-temporal","title":"Effective Distant Supervision for Temporal Relation Extraction","date":"2020-10-24","arxiv_id":"2010.12755","n_code_links":2,"syntology":null},{"paper":"/paper/hierarchical-transformer-for-task-oriented","slug":"hierarchical-transformer-for-task-oriented","title":"Hierarchical Transformer for Task Oriented Dialog Systems","date":"2020-10-24","arxiv_id":"2011.08067","n_code_links":2,"syntology":null},{"paper":"/paper/measuring-association-between-labels-and-free","slug":"measuring-association-between-labels-and-free","title":"Measuring Association Between Labels and Free-Text Rationales","date":"2020-10-24","arxiv_id":"2010.12762","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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allenai/label_rationale_association"],"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":"/paper/multi-domain-dialogue-state-tracking-a-purely","slug":"multi-domain-dialogue-state-tracking-a-purely","title":"Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking","date":"2020-10-24","arxiv_id":"2010.14061","n_code_links":2,"syntology":null},{"paper":null,"slug":"open-domain-dialogue-generation-based-on-pre","title":"Open-Domain Dialogue Generation Based on Pre-trained Language Models","date":"2020-10-24","arxiv_id":"2010.12780","n_code_links":0,"syntology":null},{"paper":null,"slug":"pep-parameter-ensembling-by-perturbation","title":"PEP: Parameter Ensembling by Perturbation","date":"2020-10-24","arxiv_id":"2010.12721","n_code_links":0,"syntology":null},{"paper":null,"slug":"persian-handwritten-digit-character-and-words","title":"Persian Handwritten Digit, Character and Word Recognition Using Deep Learning","date":"2020-10-24","arxiv_id":"2010.12880","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-summarization-distillation","slug":"pre-trained-summarization-distillation","title":"Pre-trained Summarization Distillation","date":"2020-10-24","arxiv_id":"2010.13002","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","n_code_links":4,"syntology":null},{"paper":null,"slug":"stable-resnet","title":"Stable ResNet","date":"2020-10-24","arxiv_id":"2010.12859","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paraphrase-generation-via","title":"Unsupervised Paraphrasing with Pretrained Language Models","date":"2020-10-24","arxiv_id":"2010.12885","n_code_links":0,"syntology":null},{"paper":"/paper/video-understanding-based-on-human-action-and","slug":"video-understanding-based-on-human-action-and","title":"Improved Actor Relation Graph based Group Activity Recognition","date":"2020-10-24","arxiv_id":"2010.12968","n_code_links":1,"syntology":null}],"record_sha256":"7cf9ef107525cf0d0726b433ab50d698e37d2d673ee244aeb0855cc73657ad7c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}