{"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/adam/papers/212","list_of":"/method/adam","method":"Adam","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":212,"pages_in_order":244,"rows_per_page":100,"rows":[21101,21200],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/211","next":"/method/adam/papers/213","papers":[{"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/two-level-k-fac-preconditioning-for-deep","slug":"two-level-k-fac-preconditioning-for-deep","title":"Two-Level K-FAC Preconditioning for Deep Learning","date":"2020-11-01","arxiv_id":"2011.00573","n_code_links":1,"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":"/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":"/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":"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":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":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/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":"/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":"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/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":"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":"/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":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":"adam-with-bandit-sampling-for-deep-learning","title":"Adam with Bandit Sampling for Deep Learning","date":"2020-10-24","arxiv_id":"2010.12986","n_code_links":0,"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/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":"/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":"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":null,"slug":"a-pre-training-strategy-for-recommendation","title":"Pre-training Graph Transformer with Multimodal Side Information for Recommendation","date":"2020-10-23","arxiv_id":"2010.12284","n_code_links":0,"syntology":null},{"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/barthez-a-skilled-pretrained-french-sequence","slug":"barthez-a-skilled-pretrained-french-sequence","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","date":"2020-10-23","arxiv_id":"2010.12321","n_code_links":5,"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/did-you-ask-a-good-question-a-cross-domain","slug":"did-you-ask-a-good-question-a-cross-domain","title":"Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text-to-SQL","date":"2020-10-23","arxiv_id":"2010.12634","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":"/paper/ernie-gram-pre-training-with-explicitly-n","slug":"ernie-gram-pre-training-with-explicitly-n","title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","date":"2020-10-23","arxiv_id":"2010.12148","n_code_links":2,"syntology":null},{"paper":null,"slug":"gibert-introducing-linguistic-knowledge-into","title":"GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method","date":"2020-10-23","arxiv_id":"2010.12532","n_code_links":0,"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/hatebert-retraining-bert-for-abusive-language","slug":"hatebert-retraining-bert-for-abusive-language","title":"HateBERT: Retraining BERT for Abusive Language Detection in English","date":"2020-10-23","arxiv_id":"2010.12472","n_code_links":1,"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":"/paper/long-document-ranking-with-query-directed","slug":"long-document-ranking-with-query-directed","title":"Long Document Ranking with Query-Directed Sparse Transformer","date":"2020-10-23","arxiv_id":"2010.12683","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-bert-post-pretraining-alignment","title":"Multilingual BERT Post-Pretraining Alignment","date":"2020-10-23","arxiv_id":"2010.12547","n_code_links":0,"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":"/paper/posterior-differential-regularization-with-f","slug":"posterior-differential-regularization-with-f","title":"Posterior Differential Regularization with f-divergence for Improving Model Robustness","date":"2020-10-23","arxiv_id":"2010.12638","n_code_links":2,"syntology":null},{"paper":null,"slug":"pre-trained-model-for-chinese-word","title":"Pre-training with Meta Learning for Chinese Word Segmentation","date":"2020-10-23","arxiv_id":"2010.12272","n_code_links":0,"syntology":null},{"paper":null,"slug":"st-bert-cross-modal-language-model-pre","title":"ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding","date":"2020-10-23","arxiv_id":"2010.12283","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":null,"slug":"topic-modeling-with-contextualized-word","title":"Topic Modeling with Contextualized Word Representation Clusters","date":"2020-10-23","arxiv_id":"2010.12626","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/distilling-dense-representations-for-ranking","slug":"distilling-dense-representations-for-ranking","title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers","date":"2020-10-22","arxiv_id":"2010.11386","n_code_links":2,"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/improving-bert-performance-for-aspect-based","slug":"improving-bert-performance-for-aspect-based","title":"Improving BERT Performance for Aspect-Based Sentiment Analysis","date":"2020-10-22","arxiv_id":"2010.11731","n_code_links":2,"syntology":{"ran":7,"of":11,"n_ran_checked":4,"n_instrument":3,"unverified":4,"pointer_only":2,"phrase":"7 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["IMPLabUniPr/BERT-for-ABSA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/investigating-the-true-performance-of","slug":"investigating-the-true-performance-of","title":"Exploiting News Article Structure for Automatic Corpus Generation of Entailment Datasets","date":"2020-10-22","arxiv_id":"2010.11574","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-for-bert-unsupervised","slug":"knowledge-distillation-for-bert-unsupervised","title":"Knowledge Distillation for BERT Unsupervised Domain Adaptation","date":"2020-10-22","arxiv_id":"2010.11478","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-are-open-knowledge-graphs-1","slug":"language-models-are-open-knowledge-graphs-1","title":"Language Models are Open Knowledge Graphs","date":"2020-10-22","arxiv_id":"2010.11967","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":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":null,"slug":"optimizing-coverage-and-capacity-in-cellular","title":"Optimizing Coverage and Capacity in Cellular Networks using Machine Learning","date":"2020-10-22","arxiv_id":"2010.13710","n_code_links":0,"syntology":null},{"paper":"/paper/self-alignment-pre-training-for-biomedical","slug":"self-alignment-pre-training-for-biomedical","title":"Self-Alignment Pretraining for Biomedical Entity Representations","date":"2020-10-22","arxiv_id":"2010.11784","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-fully-bilingual-deep-language","title":"Towards Fully Bilingual Deep Language Modeling","date":"2020-10-22","arxiv_id":"2010.11639","n_code_links":0,"syntology":null},{"paper":null,"slug":"unicase-rethinking-casing-in-language-models","title":"UniCase -- Rethinking Casing in Language Models","date":"2020-10-22","arxiv_id":"2010.11936","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-gradient-method-with-resilience-and-1","title":"Adaptive Gradient Method with Resilience and Momentum","date":"2020-10-21","arxiv_id":"2010.11041","n_code_links":0,"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":null,"slug":"detection-of-covid-19-informative-tweets","title":"Detection of COVID-19 informative tweets using RoBERTa","date":"2020-10-21","arxiv_id":"2010.11238","n_code_links":0,"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":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","n_code_links":1,"syntology":null},{"paper":null,"slug":"latte-mix-measuring-sentence-semantic","title":"Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures","date":"2020-10-21","arxiv_id":"2010.11351","n_code_links":0,"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":null,"slug":"transferable-graph-optimizers-for-ml","title":"Transferable Graph Optimizers for ML Compilers","date":"2020-10-21","arxiv_id":"2010.12438","n_code_links":0,"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}],"record_sha256":"ccc857b8a2895684ae55b27866eb4ee4efe32a5798727537b5c6bea866d1b2dd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}