{"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/linear-warmup-with-linear-decay/papers/48","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear Decay","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":48,"pages_in_order":71,"rows_per_page":100,"rows":[4701,4800],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/47","next":"/method/linear-warmup-with-linear-decay/papers/49","papers":[{"paper":"/paper/neural-abstractive-unsupervised-summarization","slug":"neural-abstractive-unsupervised-summarization","title":"Neural Abstractive Unsupervised Summarization of Online News Discussions","date":"2021-06-07","arxiv_id":"2106.03953","n_code_links":1,"syntology":null},{"paper":null,"slug":"never-guess-what-i-heard-rumor-detection-in","title":"Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline","date":"2021-06-07","arxiv_id":"2106.03389","n_code_links":0,"syntology":null},{"paper":"/paper/causal-abstractions-of-neural-networks","slug":"causal-abstractions-of-neural-networks","title":"Causal Abstractions of Neural Networks","date":"2021-06-06","arxiv_id":"2106.02997","n_code_links":1,"syntology":null},{"paper":null,"slug":"transient-chaos-in-bert","title":"Transient Chaos in BERT","date":"2021-06-06","arxiv_id":"2106.03181","n_code_links":0,"syntology":null},{"paper":"/paper/bertnesia-investigating-the-capture-and-1","slug":"bertnesia-investigating-the-capture-and-1","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","date":"2021-06-05","arxiv_id":"2106.02902","n_code_links":1,"syntology":null},{"paper":"/paper/bert-based-sentiment-analysis-a-software","slug":"bert-based-sentiment-analysis-a-software","title":"BERT-Based Sentiment Analysis: A Software Engineering Perspective","date":"2021-06-04","arxiv_id":"2106.02581","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-syntactic-probes-probe-syntax-experiments","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","date":"2021-06-04","arxiv_id":"2106.02559","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-tiny-a-progressive-distillation","slug":"ernie-tiny-a-progressive-distillation","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","date":"2021-06-04","arxiv_id":"2106.02241","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-equal-gender-representation-in-the","title":"Towards Equal Gender Representation in the Annotations of Toxic Language Detection","date":"2021-06-04","arxiv_id":"2106.02183","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-compress-once-towards-effective-and","slug":"you-only-compress-once-towards-effective-and","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","date":"2021-06-04","arxiv_id":"2106.02435","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-tagging-of-short-conversational","title":"Auto-tagging of Short Conversational Sentences using Transformer Methods","date":"2021-06-03","arxiv_id":"2106.01735","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-meets-liwc-exploring-state-of-the-art","title":"BERT meets LIWC: Exploring State-of-the-Art Language Models for Predicting Communication Behavior in Couples' Conflict Interactions","date":"2021-06-03","arxiv_id":"2106.01536","n_code_links":0,"syntology":null},{"paper":"/paper/ccpm-a-chinese-classical-poetry-matching","slug":"ccpm-a-chinese-classical-poetry-matching","title":"CCPM: A Chinese Classical Poetry Matching Dataset","date":"2021-06-03","arxiv_id":"2106.01979","n_code_links":1,"syntology":null},{"paper":null,"slug":"defending-democracy-using-deep-learning-to","title":"Defending Democracy: Using Deep Learning to Identify and Prevent Misinformation","date":"2021-06-03","arxiv_id":"2106.02607","n_code_links":0,"syntology":null},{"paper":"/paper/generate-prune-select-a-pipeline-for","slug":"generate-prune-select-a-pipeline-for","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","date":"2021-06-03","arxiv_id":"2106.01625","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: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["WanzhengZhu/GPS"],"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":"/paper/self-guided-contrastive-learning-for-bert","slug":"self-guided-contrastive-learning-for-bert","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","date":"2021-06-03","arxiv_id":"2106.07345","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["galsang/SG-BERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/template-based-named-entity-recognition-using","slug":"template-based-named-entity-recognition-using","title":"Template-Based Named Entity Recognition Using BART","date":"2021-06-03","arxiv_id":"2106.01760","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-limitations-of-limited-context-for","title":"The Limitations of Limited Context for Constituency Parsing","date":"2021-06-03","arxiv_id":"2106.01580","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-made-me-feel-this-way-investigating","title":"\"You made me feel this way\": Investigating Partners' Influence in Predicting Emotions in Couples' Conflict Interactions using Speech Data","date":"2021-06-03","arxiv_id":"2106.01526","n_code_links":0,"syntology":null},{"paper":null,"slug":"belabbert-a-dutch-roberta-based-language","title":"belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification","date":"2021-06-02","arxiv_id":"2106.01091","n_code_links":0,"syntology":null},{"paper":"/paper/differential-privacy-for-text-analytics-via","slug":"differential-privacy-for-text-analytics-via","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","date":"2021-06-02","arxiv_id":"2106.01221","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":["xiangyue9607/SanText"],"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/evaluating-the-efficacy-of-summarization","slug":"evaluating-the-efficacy-of-summarization","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","date":"2021-06-02","arxiv_id":"2106.01478","n_code_links":1,"syntology":null},{"paper":"/paper/mathbert-a-pre-trained-language-model-for","slug":"mathbert-a-pre-trained-language-model-for","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","date":"2021-06-02","arxiv_id":"2106.07340","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["tbs17/MathBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-distribution-sparsity-and-inference","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","date":"2021-06-02","arxiv_id":"2106.01335","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-document-similarity-ranking","slug":"self-supervised-document-similarity-ranking","title":"Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference","date":"2021-06-02","arxiv_id":"2106.01186","n_code_links":1,"syntology":null},{"paper":null,"slug":"t-bert-model-for-sentiment-analysis-of-micro","title":"T-BERT -- Model for Sentiment Analysis of Micro-blogs Integrating Topic Model and BERT","date":"2021-06-02","arxiv_id":"2106.01097","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-architecture-for-accelerated-large-scale","title":"An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-and-generalized-sentence","title":"Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-effective-deployment-of-bert-models-in-1","title":"Cost-effective Deployment of BERT Models in Serverless Environment","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cultural-and-geographical-influences-on-image","slug":"cultural-and-geographical-influences-on-image","title":"Cultural and Geographical Influences on Image Translatability of Words across Languages","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/domain-adaptation-for-arabic-cross-domain-and","slug":"domain-adaptation-for-arabic-cross-domain-and","title":"Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dreca-a-general-task-augmentation-strategy","title":"DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-objective-fine-tuning-of-bert-for-entity","slug":"dual-objective-fine-tuning-of-bert-for-entity","title":"Dual-Objective Fine-Tuning of BERT for Entity Matching","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emotion-infused-models-for-explainable","slug":"emotion-infused-models-for-explainable","title":"Emotion-Infused Models for Explainable Psychological Stress Detection","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-multihop-retrieval-for","slug":"end-to-end-multihop-retrieval-for","title":"Iterative Hierarchical Attention for Answering Complex Questions over Long Documents","date":"2021-06-01","arxiv_id":"2106.00200","n_code_links":0,"syntology":null},{"paper":"/paper/honest-measuring-hurtful-sentence-completion","slug":"honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-automatic-hate-speech-detection","title":"Improving Automatic Hate Speech Detection with Multiword Expression Features","date":"2021-06-01","arxiv_id":"2106.00237","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-grained-knowledge-distillation-for","title":"Multi-Grained Knowledge Distillation for Named Entity Recognition","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"negation-typology-and-general-representation","title":"Negation typology and general representation models for cross-lingual zero-shot negation scope resolution in Russian, French, and Spanish.","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-using-distributed-representations-of","slug":"on-using-distributed-representations-of","title":"On using distributed representations of source code for the detection of C security vulnerabilities","date":"2021-06-01","arxiv_id":"2106.01367","n_code_links":1,"syntology":null},{"paper":null,"slug":"quadrupletbert-an-efficient-model-for","title":"QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"script-self-critic-pretraining-of","title":"SCRIPT: Self-Critic PreTraining of Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shuffled-token-detection-for-refining-pre","title":"Shuffled-token Detection for Refining Pre-trained RoBERTa","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-comprehensive-understanding-and","title":"Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-language-models-under-resource","title":"Training Language Models under Resource Constraints for Adversarial Advertisement Detection","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"using-integrated-gradients-to-explain","title":"Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT","date":"2021-06-01","arxiv_id":"2106.07349","n_code_links":0,"syntology":null},{"paper":null,"slug":"wikitalkedit-a-dataset-for-modeling-editors","title":"WikiTalkEdit: A Dataset for modeling Editors' behaviors on Wikipedia","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/you-only-look-at-one-sequence-rethinking","slug":"you-only-look-at-one-sequence-rethinking","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","date":"2021-06-01","arxiv_id":"2106.00666","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":2,"n_instrument":3,"unverified":5,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hustvl/YOLOS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-transfer-learning-impacts-linguistic","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","date":"2021-05-31","arxiv_id":"2105.15179","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-electra-augmented-with-multi-word","title":"Training ELECTRA Augmented with Multi-word Selection","date":"2021-05-31","arxiv_id":"2106.00139","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-fact-verification-by-claim","slug":"zero-shot-fact-verification-by-claim","title":"Zero-shot Fact Verification by Claim Generation","date":"2021-05-31","arxiv_id":"2105.14682","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["teacherpeterpan/Zero-shot-Fact-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"a-compression-compilation-framework-for-on","title":"A Compression-Compilation Framework for On-mobile Real-time BERT Applications","date":"2021-05-30","arxiv_id":"2106.00526","n_code_links":0,"syntology":null},{"paper":"/paper/human-interpretable-ai-enhancing-tsetlin","slug":"human-interpretable-ai-enhancing-tsetlin","title":"Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine","date":"2021-05-30","arxiv_id":"2105.14506","n_code_links":7,"syntology":null},{"paper":"/paper/lrtuner-a-learning-rate-tuner-for-deep-neural","slug":"lrtuner-a-learning-rate-tuner-for-deep-neural","title":"LRTuner: A Learning Rate Tuner for Deep Neural Networks","date":"2021-05-30","arxiv_id":"2105.14526","n_code_links":2,"syntology":null},{"paper":"/paper/mlpruning-a-multilevel-structured-pruning","slug":"mlpruning-a-multilevel-structured-pruning","title":"LEAP: Learnable Pruning for Transformer-based Models","date":"2021-05-30","arxiv_id":"2105.14636","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yaozhewei/mlpruning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nas-bert-task-agnostic-and-adaptive-size-bert","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","date":"2021-05-30","arxiv_id":"2105.14444","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-models-for-offensive-language","title":"Neural Models for Offensive Language Detection","date":"2021-05-30","arxiv_id":"2106.14609","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-simple-voting-mechanism-for-online-sexist","title":"A Simple Voting Mechanism for Online Sexist Content Identification","date":"2021-05-29","arxiv_id":"2105.14309","n_code_links":0,"syntology":null},{"paper":"/paper/constructing-flow-graphs-from-procedural","slug":"constructing-flow-graphs-from-procedural","title":"Constructing Flow Graphs from Procedural Cybersecurity Texts","date":"2021-05-29","arxiv_id":"2105.14357","n_code_links":1,"syntology":null},{"paper":"/paper/sentiment-analysis-in-tweets-an-assessment","slug":"sentiment-analysis-in-tweets-an-assessment","title":"Sentiment analysis in tweets: an assessment study from classical to modern text representation models","date":"2021-05-29","arxiv_id":"2105.14373","n_code_links":1,"syntology":null},{"paper":"/paper/accelerating-bert-inference-for-sequence","slug":"accelerating-bert-inference-for-sequence","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","date":"2021-05-28","arxiv_id":"2105.13878","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-adaptive-pretraining-methods-for","title":"Domain-Adaptive Pretraining Methods for Dialogue Understanding","date":"2021-05-28","arxiv_id":"2105.13665","n_code_links":0,"syntology":null},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/weighted-training-for-cross-task-learning","slug":"weighted-training-for-cross-task-learning","title":"Weighted Training for Cross-Task Learning","date":"2021-05-28","arxiv_id":"2105.14095","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["HornHehhf/TAWT"],"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":"contrastive-fine-tuning-improves-robustness","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","date":"2021-05-27","arxiv_id":"2105.12932","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-linguistic-coordination-in","title":"Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT","date":"2021-05-27","arxiv_id":"2105.13479","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixqa-embedding-and-answer-mixing-for","title":"MixQA: Embedding and Answer Mixing for Question Answering","date":"2021-05-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"path-based-knowledge-reasoning-with-textual","title":"Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion","date":"2021-05-27","arxiv_id":"2105.13074","n_code_links":0,"syntology":null},{"paper":"/paper/raw-c-relatedness-of-ambiguous-words-in","slug":"raw-c-relatedness-of-ambiguous-words-in","title":"RAW-C: Relatedness of Ambiguous Words--in Context (A New Lexical Resource for English)","date":"2021-05-27","arxiv_id":"2105.13266","n_code_links":1,"syntology":null},{"paper":null,"slug":"verb-sense-clustering-using-contextualized","title":"Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction","date":"2021-05-27","arxiv_id":"2105.13465","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-full-stack-accelerator-search-technique-for","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","date":"2021-05-26","arxiv_id":"2105.12842","n_code_links":0,"syntology":null},{"paper":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","n_code_links":2,"syntology":{"ran":10,"of":20,"n_ran_checked":10,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"deception-detection-in-text-and-its-relation","title":"Deception detection in text and its relation to the cultural dimension of individualism/collectivism","date":"2021-05-26","arxiv_id":"2105.12530","n_code_links":0,"syntology":null},{"paper":"/paper/trade-the-event-corporate-events-detection","slug":"trade-the-event-corporate-events-detection","title":"Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading","date":"2021-05-26","arxiv_id":"2105.12825","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Zhihan1996/TradeTheEvent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"zero-shot-medical-entity-retrieval-without","title":"Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics","date":"2021-05-26","arxiv_id":"2105.12682","n_code_links":0,"syntology":null},{"paper":"/paper/consert-a-contrastive-framework-for-self","slug":"consert-a-contrastive-framework-for-self","title":"ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer","date":"2021-05-25","arxiv_id":"2105.11741","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-sensitive-visualization-of-deep","title":"Context-Sensitive Visualization of Deep Learning Natural Language Processing Models","date":"2021-05-25","arxiv_id":"2105.12202","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-multimodal-model-performance-with","slug":"enhance-multimodal-model-performance-with","title":"Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution","date":"2021-05-25","arxiv_id":"2105.13132","n_code_links":1,"syntology":null},{"paper":null,"slug":"extending-the-abstraction-of-personality","title":"Extending the Abstraction of Personality Types based on MBTI with Machine Learning and Natural Language Processing","date":"2021-05-25","arxiv_id":"2105.11798","n_code_links":0,"syntology":null},{"paper":null,"slug":"nukelm-pre-trained-and-fine-tuned-language","title":"NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains","date":"2021-05-25","arxiv_id":"2105.12192","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-transformer-for-explainable","slug":"personalized-transformer-for-explainable","title":"Personalized Transformer for Explainable Recommendation","date":"2021-05-25","arxiv_id":"2105.11601","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lileipisces/PETER"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tr-bert-dynamic-token-reduction-for","slug":"tr-bert-dynamic-token-reduction-for","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","date":"2021-05-25","arxiv_id":"2105.11618","n_code_links":1,"syntology":null},{"paper":null,"slug":"vibertgrid-a-jointly-trained-multi-modal-2d","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","date":"2021-05-25","arxiv_id":"2105.11672","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-math-kcs-via-task-adaptive-pre","title":"Classifying Math KCs via Task-Adaptive Pre-Trained BERT","date":"2021-05-24","arxiv_id":"2105.11343","n_code_links":0,"syntology":null},{"paper":"/paper/dan-danish-nested-named-entities-and-lexical","slug":"dan-danish-nested-named-entities-and-lexical","title":"DaN+: Danish Nested Named Entities and Lexical Normalization","date":"2021-05-24","arxiv_id":"2105.11301","n_code_links":1,"syntology":null},{"paper":"/paper/de-identification-of-privacy-related-entities","slug":"de-identification-of-privacy-related-entities","title":"De-identification of Privacy-related Entities in Job Postings","date":"2021-05-24","arxiv_id":"2105.11223","n_code_links":1,"syntology":null},{"paper":"/paper/diacritics-restoration-using-bert-with","slug":"diacritics-restoration-using-bert-with","title":"Diacritics Restoration using BERT with Analysis on Czech language","date":"2021-05-24","arxiv_id":"2105.11408","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ufal/bert-diacritics-restoration"],"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/fine-grained-post-training-for-improving","slug":"fine-grained-post-training-for-improving","title":"Fine-grained Post-training for Improving Retrieval-based Dialogue Systems","date":"2021-05-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/multi-modal-understanding-and-generation-for","slug":"multi-modal-understanding-and-generation-for","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","date":"2021-05-24","arxiv_id":"2105.11333","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["SuperSupermoon/MedViLL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-language-models-for-nineteenth-century","slug":"neural-language-models-for-nineteenth-century","title":"Neural Language Models for Nineteenth-Century English","date":"2021-05-24","arxiv_id":"2105.11321","n_code_links":2,"syntology":null},{"paper":"/paper/robeczech-czech-roberta-a-monolingual","slug":"robeczech-czech-roberta-a-monolingual","title":"RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model","date":"2021-05-24","arxiv_id":"2105.11314","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-adversarial-attacks-to-reveal-the","title":"Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models","date":"2021-05-24","arxiv_id":"2105.11136","n_code_links":0,"syntology":null},{"paper":"/paper/citeworth-cite-worthiness-detection-for","slug":"citeworth-cite-worthiness-detection-for","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","date":"2021-05-23","arxiv_id":"2105.10912","n_code_links":1,"syntology":null},{"paper":null,"slug":"killing-two-birds-with-one-stone-stealing","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","date":"2021-05-23","arxiv_id":"2105.10909","n_code_links":0,"syntology":null},{"paper":"/paper/autolrs-automatic-learning-rate-schedule-by-1","slug":"autolrs-automatic-learning-rate-schedule-by-1","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","date":"2021-05-22","arxiv_id":"2105.10762","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["YuchenJin/autolrs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/denoising-noisy-neural-networks-a-bayesian","slug":"denoising-noisy-neural-networks-a-bayesian","title":"Denoising Noisy Neural Networks: A Bayesian Approach with Compensation","date":"2021-05-22","arxiv_id":"2105.10699","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-visual-prototypes-with-bert","title":"Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning","date":"2021-05-21","arxiv_id":"2105.10195","n_code_links":0,"syntology":null},{"paper":null,"slug":"stance-detection-with-bert-embeddings-for","title":"Stance Detection with BERT Embeddings for Credibility Analysis of Information on Social Media","date":"2021-05-21","arxiv_id":"2105.10272","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automatic-comparison-of-data-privacy","slug":"towards-automatic-comparison-of-data-privacy","title":"Towards Automatic Comparison of Data Privacy Documents: A Preliminary Experiment on GDPR-like Laws","date":"2021-05-21","arxiv_id":"2105.10117","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-comparative-evaluation-and","slug":"a-comprehensive-comparative-evaluation-and","title":"A comparative evaluation and analysis of three generations of Distributional Semantic Models","date":"2021-05-20","arxiv_id":"2105.09825","n_code_links":1,"syntology":null}],"record_sha256":"d3768eb39d6a2ca7b060f00a177b1a62d91c50e3808c8e37bede9910a5e6ddf9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}