{"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/roberta/papers/7","list_of":"/method/roberta","method":"RoBERTa","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":7,"pages_in_order":10,"rows_per_page":100,"rows":[601,700],"of":913,"counts":{"archive_papers_tagged":913,"with_a_code_link":399,"where_syntology_ran_a_sample":87,"not_listed_spam_title":0,"listed":913,"listed_where_code_ran":87,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":66,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":66,"listed_every_run_a_failure_of_syntologys_instrument":21,"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/roberta","prev":"/method/roberta/papers/6","next":"/method/roberta/papers/8","papers":[{"paper":"/paper/models-in-a-spelling-bee-language-models","slug":"models-in-a-spelling-bee-language-models","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-08-25","arxiv_id":"2108.11193","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itay1itzhak/spellingbee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sarcasm-detection-in-twitter-performance","slug":"sarcasm-detection-in-twitter-performance","title":"Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddings","date":"2021-08-23","arxiv_id":"2108.09924","n_code_links":1,"syntology":null},{"paper":null,"slug":"maps-search-misspelling-detection-leveraging","title":"Maps Search Misspelling Detection Leveraging Domain-Augmented Contextual Representations","date":"2021-08-15","arxiv_id":"2108.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-social-and-behavioral-determinants","title":"A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models","date":"2021-08-10","arxiv_id":"2108.04949","n_code_links":0,"syntology":null},{"paper":"/paper/filming-multimodal-sarcasm-detection-with","slug":"filming-multimodal-sarcasm-detection-with","title":"FiLMing Multimodal Sarcasm Detection with Attention","date":"2021-08-09","arxiv_id":"2110.00416","n_code_links":1,"syntology":null},{"paper":null,"slug":"http2vec-embedding-of-http-requests-for","title":"HTTP2vec: Embedding of HTTP Requests for Detection of Anomalous Traffic","date":"2021-08-03","arxiv_id":"2108.01763","n_code_links":0,"syntology":null},{"paper":null,"slug":"1213li-at-semeval-2021-task-6-detection-of","title":"1213Li at SemEval-2021 Task 6: Detection of Propaganda with Multi-modal Attention and Pre-trained Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adept-an-adjective-dependent-plausibility","title":"ADEPT: An Adjective-Dependent Plausibility Task","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"astartwice-at-semeval-2021-task-5-toxic-span","title":"AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bertac-enhancing-transformer-based-language","slug":"bertac-enhancing-transformer-based-language","title":"BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"can-transformer-models-measure-coherence-in","title":"Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-evidence-improves-monolingual","slug":"cross-lingual-evidence-improves-monolingual","title":"Cross-lingual Evidence Improves Monolingual Fake News Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-1-fusion-of","title":"CSECU-DSG at SemEval-2021 Task 1: Fusion of Transformer Models for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-7-detecting","title":"CSECU-DSG at SemEval-2021 Task 7: Detecting and Rating Humor and Offense Employing Transformers","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deepblueai-at-semeval-2021-task-7-detecting","title":"DeepBlueAI at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Stacking Diverse Language Model-Based Methods","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dljust-at-semeval-2021-task-7-hahackathon","title":"DLJUST at SemEval-2021 Task 7: Hahackathon: Linking Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"es-just-at-semeval-2021-task-7-detecting-and","title":"ES-JUST at SemEval-2021 Task 7: Detecting and Rating Humor and Offensive Text Using Deep Learning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ghostbert-generate-more-features-with-cheap","title":"GhostBERT: Generate More Features with Cheap Operations for BERT","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"grenzlinie-at-semeval-2021-task-7-detecting","title":"Grenzlinie at SemEval-2021 Task 7: Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gulu-at-semeval-2021-task-7-detecting-and","title":"Gulu at SemEval-2021 Task 7: Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hamiltondinggg-at-semeval-2021-task-5","title":"HamiltonDinggg at SemEval-2021 Task 5: Investigating Toxic Span Detection using RoBERTa Pre-training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hub-at-semeval-2021-task-1-fusion-of-sentence","title":"hub at SemEval-2021 Task 1: Fusion of Sentence and Word Frequency to Predict Lexical Complexity","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hub-at-semeval-2021-task-2-word-meaning","title":"hub at SemEval-2021 Task 2: Word Meaning Similarity Prediction Model Based on RoBERTa and Word Frequency","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"just-blue-at-semeval-2021-task-1-predicting","title":"JUST-BLUE at SemEval-2021 Task 1: Predicting Lexical Complexity using BERT and RoBERTa Pre-trained Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lecun-at-semeval-2021-task-6-detecting","title":"LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"liori-at-semeval-2021-task-8-ask-transformer","title":"LIORI at SemEval-2021 Task 8: Ask Transformer for measurements","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"medai-at-semeval-2021-task-5-start-to-end","title":"MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mind-at-semeval-2021-task-6-propaganda","title":"MinD at SemEval-2021 Task 6: Propaganda Detection using Transfer Learning and Multimodal Fusion","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nlpiitr-at-semeval-2021-task-6-roberta-model","title":"NLPIITR at SemEval-2021 Task 6: RoBERTa Model with Data Augmentation for Persuasion Techniques Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nlyticsfkie-at-semeval-2021-task-6-detection","title":"NLyticsFKIE at SemEval-2021 Task 6: Detection of Persuasion Techniques In Texts And Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"paw-at-semeval-2021-task-2-multilingual-and","title":"PAW at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation : Exploring Cross Lingual Transfer, Augmentations and Adversarial Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"rg-pa-at-semeval-2021-task-1-a-contextual","title":"RG PA at SemEval-2021 Task 1: A Contextual Attention-based Model with RoBERTa for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sarcasmdet-at-semeval-2021-task-7-detect","title":"SarcasmDet at SemEval-2021 Task 7: Detect Humor and Offensive based on Demographic Factors using RoBERTa Pre-trained Model","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sefamerve-arge-at-semeval-2021-task-5-toxic","slug":"sefamerve-arge-at-semeval-2021-task-5-toxic","title":"Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"skoltechnlp-at-semeval-2021-task-5-leveraging","title":"SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ynu-hpcc-at-semeval-2021-task-5-using-a","slug":"ynu-hpcc-at-semeval-2021-task-5-using-a","title":"YNU-HPCC at SemEval-2021 Task 5: Using a Transformer-based Model with Auxiliary Information for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-text-classification-via-contrastive","title":"Improved Text Classification via Contrastive Adversarial Training","date":"2021-07-21","arxiv_id":"2107.10137","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-vector-based-approach-to-few-shot-veracity","title":"A Vector-Based Approach to Few-Shot Veracity Classification for Automated Fact-Checking","date":"2021-07-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-learning-query-and-product","title":"Neural Search: Learning Query and Product Representations in Fashion E-commerce","date":"2021-07-17","arxiv_id":"2107.08291","n_code_links":0,"syntology":null},{"paper":"/paper/fewclue-a-chinese-few-shot-learning","slug":"fewclue-a-chinese-few-shot-learning","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","date":"2021-07-15","arxiv_id":"2107.07498","n_code_links":1,"syntology":null},{"paper":"/paper/trusting-roberta-over-bert-insights-from","slug":"trusting-roberta-over-bert-insights-from","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","date":"2021-07-15","arxiv_id":"2107.07229","n_code_links":1,"syntology":null},{"paper":"/paper/what-do-writing-features-tell-us-about-ai","slug":"what-do-writing-features-tell-us-about-ai","title":"What do writing features tell us about AI papers?","date":"2021-07-13","arxiv_id":"2107.06310","n_code_links":1,"syntology":null},{"paper":"/paper/a-review-of-bangla-natural-language","slug":"a-review-of-bangla-natural-language","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","date":"2021-07-08","arxiv_id":"2107.03844","n_code_links":2,"syntology":null},{"paper":"/paper/can-transformer-models-measure-coherence-in-1","slug":"can-transformer-models-measure-coherence-in-1","title":"Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test","date":"2021-07-07","arxiv_id":"2107.03448","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-domain-agnostic-and-specific","title":"Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation","date":"2021-07-01","arxiv_id":"2107.00316","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-generalization-for-intent","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","date":"2021-06-28","arxiv_id":"2106.14464","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-differential-privacy-and","slug":"benchmarking-differential-privacy-and","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","date":"2021-06-26","arxiv_id":"2106.13973","n_code_links":1,"syntology":null},{"paper":"/paper/context-aware-legal-citation-recommendation","slug":"context-aware-legal-citation-recommendation","title":"Context-Aware Legal Citation Recommendation using Deep Learning","date":"2021-06-20","arxiv_id":"2106.10776","n_code_links":1,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/cblue-a-chinese-biomedical-language","slug":"cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","arxiv_id":"2106.08087","n_code_links":2,"syntology":{"ran":11,"of":16,"n_ran_checked":8,"n_instrument":3,"unverified":5,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cbluebenchmark/cblue"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"why-can-you-lay-off-heads-investigating-how","title":"Why Can You Lay Off Heads? Investigating How BERT Heads Transfer","date":"2021-06-14","arxiv_id":"2106.07137","n_code_links":0,"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":"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":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":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":"/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/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":"/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":"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":"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":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":"/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":"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":"/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":null,"slug":"fine-tuned-transformers-show-clusters-of-1","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","date":"2021-05-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/how-is-bert-surprised-layerwise-detection-of","slug":"how-is-bert-surprised-layerwise-detection-of","title":"How is BERT surprised? Layerwise detection of linguistic anomalies","date":"2021-05-16","arxiv_id":"2105.07452","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-gender-bias-in-natural-language-1","slug":"evaluating-gender-bias-in-natural-language-1","title":"Evaluating Gender Bias in Natural Language Inference","date":"2021-05-12","arxiv_id":"2105.05541","n_code_links":1,"syntology":null},{"paper":null,"slug":"go-beyond-plain-fine-tuning-improving","title":"Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense","date":"2021-05-12","arxiv_id":"2105.05913","n_code_links":0,"syntology":null},{"paper":"/paper/kleister-key-information-extraction-datasets","slug":"kleister-key-information-extraction-datasets","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","date":"2021-05-12","arxiv_id":"2105.05796","n_code_links":0,"syntology":null},{"paper":"/paper/mate-kd-masked-adversarial-text-a-companion","slug":"mate-kd-masked-adversarial-text-a-companion","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","date":"2021-05-12","arxiv_id":"2105.05912","n_code_links":1,"syntology":null},{"paper":"/paper/bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","slug":"bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","date":"2021-05-11","arxiv_id":"2105.04949","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-the-syntactic-capabilities-of","title":"Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models","date":"2021-05-10","arxiv_id":"2105.04688","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-evaluation-of-pre-trained","slug":"empirical-evaluation-of-pre-trained","title":"Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality","date":"2021-05-07","arxiv_id":"2105.03484","n_code_links":1,"syntology":null},{"paper":"/paper/melbert-metaphor-detection-via-contextualized","slug":"melbert-metaphor-detection-via-contextualized","title":"MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories","date":"2021-04-28","arxiv_id":"2104.13615","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jin530/MelBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"uot-uwf-partai-at-semeval-2021-task-5-self","title":"UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter","date":"2021-04-27","arxiv_id":"2104.13164","n_code_links":0,"syntology":null},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","n_code_links":5,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 4 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) · 4 unverified","official":{"repos":["ashkamath/mdetr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"comparative-analysis-of-machine-learning-and","title":"Comparative Analysis of Machine Learning and Deep Learning Algorithms for Detection of Online Hate Speech","date":"2021-04-23","arxiv_id":"2108.01063","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-small-berts-trained-for-german-ner","slug":"optimizing-small-berts-trained-for-german-ner","title":"Optimizing small BERTs trained for German NER","date":"2021-04-23","arxiv_id":"2104.11559","n_code_links":2,"syntology":null},{"paper":null,"slug":"discriminative-self-training-for-punctuation","title":"Discriminative Self-training for Punctuation Prediction","date":"2021-04-21","arxiv_id":"2104.10339","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-pre-training-objectives-for","title":"Efficient pre-training objectives for Transformers","date":"2021-04-20","arxiv_id":"2104.09694","n_code_links":0,"syntology":null},{"paper":"/paper/subsentence-extraction-from-text-using","slug":"subsentence-extraction-from-text-using","title":"Subsentence Extraction from Text Using Coverage-Based Deep Learning Language Models","date":"2021-04-20","arxiv_id":"2104.09777","n_code_links":1,"syntology":null},{"paper":null,"slug":"modeling-newsworthiness-for-lead-generation","title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora","date":"2021-04-19","arxiv_id":"2104.09653","n_code_links":0,"syntology":null},{"paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","slug":"teamuncc-lt-edi-eacl2021-hope-speech","title":"TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-topic-confusion-task-a-novel-scenario-for","title":"The Topic Confusion Task: A Novel Scenario for Authorship Attribution","date":"2021-04-17","arxiv_id":"2104.08530","n_code_links":0,"syntology":null},{"paper":"/paper/probing-across-time-what-does-roberta-know","slug":"probing-across-time-what-does-roberta-know","title":"Probing Across Time: What Does RoBERTa Know and When?","date":"2021-04-16","arxiv_id":"2104.07885","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["leo-liuzy/probe-across-time"],"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/bert-based-transformers-lead-the-way-in","slug":"bert-based-transformers-lead-the-way-in","title":"BERT based Transformers lead the way in Extraction of Health Information from Social Media","date":"2021-04-15","arxiv_id":"2104.07367","n_code_links":1,"syntology":null},{"paper":"/paper/torontocl-at-cmcl-2021-shared-task-roberta","slug":"torontocl-at-cmcl-2021-shared-task-roberta","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","date":"2021-04-15","arxiv_id":"2104.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"uit-e10dot3-at-semeval-2021-task-5-toxic","title":"UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches","date":"2021-04-15","arxiv_id":"2104.07376","n_code_links":0,"syntology":null},{"paper":"/paper/does-syntax-matter-a-strong-baseline-for","slug":"does-syntax-matter-a-strong-baseline-for","title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","date":"2021-04-11","arxiv_id":"2104.04986","n_code_links":1,"syntology":null},{"paper":"/paper/unidrop-a-simple-yet-effective-technique-to","slug":"unidrop-a-simple-yet-effective-technique-to","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","date":"2021-04-11","arxiv_id":"2104.04946","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-the-end-of-history-for-nlp","title":"Transformers: \"The End of History\" for NLP?","date":"2021-04-09","arxiv_id":"2105.00813","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-transformers-in-emotion-recognition","title":"Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA","date":"2021-04-05","arxiv_id":"2104.02041","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-distance-a-new-metric-for-asr","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","date":"2021-04-05","arxiv_id":"2104.02138","n_code_links":0,"syntology":null},{"paper":null,"slug":"content-based-models-of-quotation","title":"Content-based Models of Quotation","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/nlquad-a-non-factoid-long-question-answering","slug":"nlquad-a-non-factoid-long-question-answering","title":"NLQuAD: A Non-Factoid Long Question Answering Data Set","date":"2021-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"retraining-distilbert-for-a-voice-shopping","title":"Retraining DistilBERT for a Voice Shopping Assistant by Using Universal Dependencies","date":"2021-03-29","arxiv_id":"2103.15737","n_code_links":0,"syntology":null}],"record_sha256":"1e0f026c0901261457f6c1296429baf22a28f40e63d79f8d8368c53401ef8299","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}