{"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/deberta","slug":"deberta","name":"DeBERTa","full_name":"DeBERTa","full_name_withheld":false,"description_markdown":"**DeBERTa** is a [Transformer](https://paperswithcode.com/methods/category/transformers)-based neural language model that aims to improve the [BERT](https://paperswithcode.com/method/bert) and [RoBERTa](https://paperswithcode.com/method/roberta) models with two techniques: a [disentangled attention mechanism](https://paperswithcode.com/method/disentangled-attention-mechanism) and an enhanced mask decoder. The disentangled attention mechanism is where each word is represented unchanged using two vectors that encode its content and position, respectively, and the attention weights among words are computed using disentangle matrices on their contents and relative positions. The enhanced mask decoder is used to replace the output [softmax](https://paperswithcode.com/method/softmax) layer to predict the masked tokens for model pre-training.  In addition, a new virtual adversarial training method is used for fine-tuning to improve model’s generalization on downstream tasks.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","paper":"/paper/deberta-decoding-enhanced-bert-with","first_author":"Pengcheng He","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deberta-decoding-enhanced-bert-with"},"source":{"url":"https://arxiv.org/abs/2006.03654v6","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Autoencoding Transformers","url":"/methods/category/autoencoding-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":90,"archive_num_papers":90,"papers_newest_first":[{"paper":"/paper/ai-wizards-at-checkthat-2025-enhancing","slug":"ai-wizards-at-checkthat-2025-enhancing","title":"AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles","date":"2025-07-15","arxiv_id":"2507.11764","n_code_links":1,"syntology":null},{"paper":null,"slug":"plantbert-an-open-source-language-model-for","title":"PlantBert: An Open Source Language Model for Plant Science","date":"2025-06-10","arxiv_id":"2506.08897","n_code_links":0,"syntology":null},{"paper":null,"slug":"weightlora-keep-only-necessary-adapters","title":"WeightLoRA: Keep Only Necessary Adapters","date":"2025-06-03","arxiv_id":"2506.02724","n_code_links":0,"syntology":null},{"paper":null,"slug":"decom-renorm-merge-model-merging-on-the-right","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","date":"2025-05-29","arxiv_id":"2505.23117","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-named-entity-recognition-2","slug":"transformer-based-named-entity-recognition-2","title":"Transformer-Based Named Entity Recognition for Automated Server Provisioning","date":"2025-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sarang-at-defactify-4-0-detecting-ai","title":"Sarang at DEFACTIFY 4.0: Detecting AI-Generated Text Using Noised Data and an Ensemble of DeBERTa Models","date":"2025-02-24","arxiv_id":"2502.16857","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-mixed-telugu-english-hate-speech","title":"Code-Mixed Telugu-English Hate Speech Detection","date":"2025-02-15","arxiv_id":"2502.10632","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-belief-a-hard-problem-for-llms","title":"Zero-Shot Belief: A Hard Problem for LLMs","date":"2025-02-12","arxiv_id":"2502.08777","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-safety-classification-using","title":"Lightweight Safety Classification Using Pruned Language Models","date":"2024-12-18","arxiv_id":"2412.13435","n_code_links":0,"syntology":null},{"paper":"/paper/seke-specialised-experts-for-keyword","slug":"seke-specialised-experts-for-keyword","title":"SEKE: Specialised Experts for Keyword Extraction","date":"2024-12-18","arxiv_id":"2412.14087","n_code_links":1,"syntology":null},{"paper":null,"slug":"ragulator-lightweight-out-of-context","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","date":"2024-11-06","arxiv_id":"2411.03920","n_code_links":0,"syntology":null},{"paper":"/paper/bonafide-at-legallens-2024-shared-task-using","slug":"bonafide-at-legallens-2024-shared-task-using","title":"Bonafide at LegalLens 2024 Shared Task: Using Lightweight DeBERTa Based Encoder For Legal Violation Detection and Resolution","date":"2024-10-30","arxiv_id":"2410.22977","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-transformer-models-for-suicide","title":"Evaluating Transformer Models for Suicide Risk Detection on Social Media","date":"2024-10-10","arxiv_id":"2410.08375","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-coherent-explanation-generation-of","slug":"multimodal-coherent-explanation-generation-of","title":"Multimodal Coherent Explanation Generation of Robot Failures","date":"2024-10-01","arxiv_id":"2410.00659","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-academic-skills-assessment-with-nlp","title":"Improving Academic Skills Assessment with NLP and Ensemble Learning","date":"2024-09-23","arxiv_id":"2409.19013","n_code_links":0,"syntology":null},{"paper":null,"slug":"instruct-deberta-a-hybrid-approach-for-aspect","title":"Instruct-DeBERTa: A Hybrid Approach for Aspect-based Sentiment Analysis on Textual Reviews","date":"2024-08-23","arxiv_id":"2408.13202","n_code_links":0,"syntology":null},{"paper":"/paper/scientific-qa-system-with-verifiable-answers","slug":"scientific-qa-system-with-verifiable-answers","title":"Scientific QA System with Verifiable Answers","date":"2024-07-16","arxiv_id":"2407.11485","n_code_links":1,"syntology":null},{"paper":null,"slug":"turn-level-empathy-prediction-using","title":"Turn-Level Empathy Prediction Using Psychological Indicators","date":"2024-07-11","arxiv_id":"2407.08607","n_code_links":0,"syntology":null},{"paper":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","n_code_links":0,"syntology":null},{"paper":"/paper/berts-are-generative-in-context-learners","slug":"berts-are-generative-in-context-learners","title":"BERTs are Generative In-Context Learners","date":"2024-06-07","arxiv_id":"2406.04823","n_code_links":1,"syntology":{"ran":13,"of":26,"n_ran_checked":11,"n_instrument":2,"unverified":13,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["ltgoslo/bert-in-context"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":"/paper/modeling-emotional-trajectories-in-written","slug":"modeling-emotional-trajectories-in-written","title":"Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-Supervised Learning","date":"2024-06-04","arxiv_id":"2406.02251","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-automatic-grading-with-neural","title":"Explainable Automatic Grading with Neural Additive Models","date":"2024-05-01","arxiv_id":"2405.00489","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-analysis-of-deep-natural-networks","slug":"comparative-analysis-of-deep-natural-networks","title":"Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dke-research-at-semeval-2024-task-2","title":"DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness","date":"2024-04-14","arxiv_id":"2404.09206","n_code_links":0,"syntology":null},{"paper":"/paper/tldr-at-semeval-2024-task-2-t5-generated","slug":"tldr-at-semeval-2024-task-2-t5-generated","title":"TLDR at SemEval-2024 Task 2: T5-generated clinical-Language summaries for DeBERTa Report Analysis","date":"2024-04-14","arxiv_id":"2404.09136","n_code_links":1,"syntology":null},{"paper":null,"slug":"drbert-unveiling-the-potential-of-masked","title":"BPDec: Unveiling the Potential of Masked Language Modeling Decoder in BERT pretraining","date":"2024-01-29","arxiv_id":"2401.15861","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-essay-scoring-with-adversarial","title":"Enhancing Essay Scoring with Adversarial Weights Perturbation and Metric-specific AttentionPooling","date":"2024-01-06","arxiv_id":"2401.05433","n_code_links":0,"syntology":null},{"paper":null,"slug":"more-than-correlation-do-large-language","title":"More than Correlation: Do Large Language Models Learn Causal Representations of Space?","date":"2023-12-26","arxiv_id":"2312.16257","n_code_links":0,"syntology":null},{"paper":"/paper/propres-investigating-the-projectivity-of","slug":"propres-investigating-the-projectivity-of","title":"PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments","date":"2023-12-14","arxiv_id":"2312.08755","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-sentiment-analysis-results-through","title":"Enhancing Sentiment Analysis Results through Outlier Detection Optimization","date":"2023-11-25","arxiv_id":"2311.16185","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-brasil-at-absapt-2022","slug":"deep-learning-brasil-at-absapt-2022","title":"Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches","date":"2023-11-08","arxiv_id":"2311.05051","n_code_links":1,"syntology":null},{"paper":"/paper/deeplearningbrasil-lt-edi-2023-exploring-deep","slug":"deeplearningbrasil-lt-edi-2023-exploring-deep","title":"DeepLearningBrasil@LT-EDI-2023: Exploring Deep Learning Techniques for Detecting Depression in Social Media Text","date":"2023-11-08","arxiv_id":"2311.05047","n_code_links":1,"syntology":null},{"paper":"/paper/interpretable-by-design-text-classification","slug":"interpretable-by-design-text-classification","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","date":"2023-10-30","arxiv_id":"2310.19660","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-ensemble-method-based-on-the-combination","title":"An Ensemble Method Based on the Combination of Transformers with Convolutional Neural Networks to Detect Artificially Generated Text","date":"2023-10-26","arxiv_id":"2310.17312","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformer-based-1","title":"A Comparative Study of Transformer-based Neural Text Representation Techniques on Bug Triaging","date":"2023-10-10","arxiv_id":"2310.06913","n_code_links":0,"syntology":null},{"paper":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","n_code_links":1,"syntology":null},{"paper":null,"slug":"arc-nlp-at-pan-2023-transition-focused","title":"ARC-NLP at PAN 2023: Transition-Focused Natural Language Inference for Writing Style Detection","date":"2023-07-27","arxiv_id":"2307.14913","n_code_links":0,"syntology":null},{"paper":null,"slug":"findings-of-factify-2-multimodal-fake-news","title":"Findings of Factify 2: Multimodal Fake News Detection","date":"2023-07-19","arxiv_id":"2307.10475","n_code_links":0,"syntology":null},{"paper":"/paper/math-word-problem-solving-by-generating","slug":"math-word-problem-solving-by-generating","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","date":"2023-06-24","arxiv_id":"2306.13899","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using","slug":"enhancing-social-network-hate-detection-using","title":"Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time","date":"2023-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/neural-models-for-factual-inconsistency","slug":"neural-models-for-factual-inconsistency","title":"Neural models for Factual Inconsistency Classification with Explanations","date":"2023-06-15","arxiv_id":"2306.08872","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-efficient-french-language-modeling-with","title":"Data-Efficient French Language Modeling with CamemBERTa","date":"2023-06-02","arxiv_id":"2306.01497","n_code_links":0,"syntology":null},{"paper":"/paper/scone-benchmarking-negation-reasoning-in","slug":"scone-benchmarking-negation-reasoning-in","title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","date":"2023-05-30","arxiv_id":"2305.19426","n_code_links":1,"syntology":null},{"paper":null,"slug":"ahead-of-time-p-tuning","title":"Ahead-of-Time P-Tuning","date":"2023-05-18","arxiv_id":"2305.10835","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-rumination-for-pre-trained-language","slug":"knowledge-rumination-for-pre-trained-language","title":"Knowledge Rumination for Pre-trained Language Models","date":"2023-05-15","arxiv_id":"2305.08732","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-neural-encoding-of-portuguese-with","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","date":"2023-05-11","arxiv_id":"2305.06721","n_code_links":0,"syntology":null},{"paper":null,"slug":"stanford-mlab-at-semeval-2023-task-10","title":"Stanford MLab at SemEval-2023 Task 10: Exploring GloVe- and Transformer-Based Methods for the Explainable Detection of Online Sexism","date":"2023-05-07","arxiv_id":"2305.04356","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-social-biases-in-recent-large","title":"Evaluation of Social Biases in Recent Large Pre-Trained Models","date":"2023-04-13","arxiv_id":"2304.06861","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-thyroid-nodules-characteristics","title":"Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods","date":"2023-03-31","arxiv_id":"2304.00115","n_code_links":0,"syntology":null},{"paper":"/paper/adapting-pretrained-language-models-for","slug":"adapting-pretrained-language-models-for","title":"Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record","date":"2023-03-27","arxiv_id":"2303.14920","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-in-the-workplace-a-case","title":"Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification","date":"2023-03-13","arxiv_id":"2303.07142","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-learning-approaches-for-classifying","title":"Few-shot learning approaches for classifying low resource domain specific software requirements","date":"2023-02-14","arxiv_id":"2302.06951","n_code_links":0,"syntology":null},{"paper":"/paper/videberta-a-powerful-pre-trained-language","slug":"videberta-a-powerful-pre-trained-language","title":"ViDeBERTa: A powerful pre-trained language model for Vietnamese","date":"2023-01-25","arxiv_id":"2301.10439","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["hysonlab/videberta"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"inpars-light-cost-effective-unsupervised","title":"InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers","date":"2023-01-08","arxiv_id":"2301.02998","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-text-detection-with-multiple","title":"Artificial Text Detection with Multiple Training Strategies","date":"2022-12-10","arxiv_id":"2212.05194","n_code_links":0,"syntology":null},{"paper":null,"slug":"x-pudu-at-semeval-2022-task-6-multilingual-1","title":"X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection","date":"2022-11-30","arxiv_id":"2211.16883","n_code_links":0,"syntology":null},{"paper":null,"slug":"mole-a-molecular-foundation-model-for-drug","title":"MolE: a molecular foundation model for drug discovery","date":"2022-11-03","arxiv_id":"2211.02657","n_code_links":0,"syntology":null},{"paper":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","n_code_links":1,"syntology":{"ran":2,"of":7,"n_ran_checked":2,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-better-your-syntax-the-better-your","title":"The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative","date":"2022-10-24","arxiv_id":"2210.13181","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-ranking-socio-political-texts-with","title":"Zero-Shot Ranking Socio-Political Texts with Transformer Language Models to Reduce Close Reading Time","date":"2022-10-17","arxiv_id":"2210.09179","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-and-strong-baseline-for-end-to-end","slug":"a-simple-and-strong-baseline-for-end-to-end","title":"A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing","date":"2022-10-15","arxiv_id":"2210.08355","n_code_links":1,"syntology":null},{"paper":"/paper/vote-n-rank-revision-of-benchmarking-with","slug":"vote-n-rank-revision-of-benchmarking-with","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","date":"2022-10-11","arxiv_id":"2210.05769","n_code_links":1,"syntology":{"ran":6,"of":17,"n_ran_checked":6,"n_instrument":0,"unverified":11,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["pragmaticslab/vote_and_rank"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/bytetransformer-a-high-performance","slug":"bytetransformer-a-high-performance","title":"ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs","date":"2022-10-06","arxiv_id":"2210.03052","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-generated-scientific-papers-using","slug":"detecting-generated-scientific-papers-using","title":"Detecting Generated Scientific Papers using an Ensemble of Transformer Models","date":"2022-09-17","arxiv_id":"2209.08283","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-for-understanding-of-english-verb","title":"Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models","date":"2022-09-11","arxiv_id":"2209.04811","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-your-model-sensitive-spedac-a-new","title":"Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data","date":"2022-08-12","arxiv_id":"2208.06216","n_code_links":0,"syntology":null},{"paper":"/paper/beike-nlp-at-semeval-2022-task-4-prompt-based-1","slug":"beike-nlp-at-semeval-2022-task-4-prompt-based-1","title":"BEIKE NLP at SemEval-2022 Task 4: Prompt-Based Paragraph Classification for Patronizing and Condescending Language Detection","date":"2022-08-02","arxiv_id":"2208.01312","n_code_links":0,"syntology":null},{"paper":"/paper/gimlps-gate-with-inhibition-mechanism-in-mlps","slug":"gimlps-gate-with-inhibition-mechanism-in-mlps","title":"giMLPs: Gate with Inhibition Mechanism in MLPs","date":"2022-08-01","arxiv_id":"2208.00929","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-cognitive-study-on-semantic-similarity","title":"A Cognitive Study on Semantic Similarity Analysis of Large Corpora: A Transformer-based Approach","date":"2022-07-24","arxiv_id":"2207.11716","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-review-and-replicability-study","slug":"a-systematic-review-and-replicability-study","title":"A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation","date":"2022-07-15","arxiv_id":"2207.07483","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["asash/bert4rec_repro"],"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","unlocated"]}}},{"paper":null,"slug":"a-novel-deberta-based-model-for-financial","title":"A Novel DeBERTa-based Model for Financial Question Answering Task","date":"2022-07-12","arxiv_id":"2207.05875","n_code_links":0,"syntology":null},{"paper":null,"slug":"aspect-based-sentiment-analysis-using-local","title":"Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa","date":"2022-07-06","arxiv_id":"2207.02424","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowda-all-in-one-knowledge-mixture-model-for","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","date":"2022-06-21","arxiv_id":"2206.10265","n_code_links":0,"syntology":null},{"paper":"/paper/fewer-errors-but-more-stereotypes-the-effect","slug":"fewer-errors-but-more-stereotypes-the-effect","title":"Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias","date":"2022-06-20","arxiv_id":"2206.09860","n_code_links":1,"syntology":null},{"paper":"/paper/scideberta-learning-deberta-for-science","slug":"scideberta-learning-deberta-for-science","title":"SciDeBERTa: Learning DeBERTa for Science Technology Documents and Fine-Tuning Information Extraction Tasks","date":"2022-06-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"rigoberta-a-state-of-the-art-language-model","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","date":"2022-04-27","arxiv_id":"2205.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"autoencoding-language-model-based-ensemble","title":"Autoencoding Language Model Based Ensemble Learning for Commonsense Validation and Explanation","date":"2022-04-07","arxiv_id":"2204.03324","n_code_links":0,"syntology":null},{"paper":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"abcbpc-at-semeval-2021-task-7-ernie-based","title":"abcbpc at SemEval-2021 Task 7: ERNIE-based Multi-task Model for Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"duluth-at-semeval-2021-task-11-applying","title":"Duluth at SemEval-2021 Task 11: Applying DeBERTa to Contributing Sentence Selection and Dependency Parsing for Entity Extraction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"humorhunter-at-semeval-2021-task-7-humor-and","title":"HumorHunter at SemEval-2021 Task 7: Humor and Offense Recognition with Disentangled Attention","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":"/paper/aspect-based-sentiment-analysis-using-bert","slug":"aspect-based-sentiment-analysis-using-bert","title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","date":"2021-07-18","arxiv_id":null,"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":43,"n_instrument":8,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 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/sas-self-augmented-strategy-for-language","slug":"sas-self-augmented-strategy-for-language","title":"SAS: Self-Augmentation Strategy for Language Model Pre-training","date":"2021-06-14","arxiv_id":"2106.07176","n_code_links":1,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","n_code_links":14,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]}}}],"papers_shown":90,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":90,"with_a_code_link":39,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":90,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/method/deberta/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/deberta/papers/ran/1","json":"/method/deberta/papers/ran/1.json","rows":8}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":25},{"task":"/task/language-modeling","name":"Language Modeling","papers":19},{"task":"/task/sentence","name":"Sentence","papers":11},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":9},{"task":"/task/question-answering","name":"Question Answering","papers":9},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":8},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":8},{"task":"/task/large-language-model","name":"Large Language Model","papers":6},{"task":"/task/aspect-based-sentiment-analysis-1","name":"Aspect-Based Sentiment Analysis","papers":5},{"task":"/task/aspect-based-sentiment-analysis","name":"Aspect-Based Sentiment Analysis (ABSA)","papers":5},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":5},{"task":"/task/articles","name":"Articles","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/hate-speech-detection","name":"Hate Speech Detection","papers":4},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":4},{"task":"/task/text-classification","name":"Text Classification","papers":4},{"task":"/task/text-generation","name":"Text Generation","papers":4},{"task":"/task/text-classification-1","name":"text-classification","papers":4},{"task":"/task/benchmarking","name":"Benchmarking","papers":3},{"task":"/task/classification-1","name":"Classification","papers":3}],"tasks_shown":20,"n_tasks":133,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":8},{"year":"2022","papers":23},{"year":"2023","papers":29},{"year":"2024","papers":21},{"year":"2025","papers":8}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deberta"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DeBERTa","read_at":"2026-10-05T00:54:33+00:00","query":"DeBERTa","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"DeBERTa","origin_arxiv_id":"2006.03654"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2006.03654","repositories":{"listed":5,"in_graph":11,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2006.03654","citations":4073},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'DeBERTa'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2006.03654","page":"/paper/deberta-decoding-enhanced-bert-with","syntology_url":"https://syntology.ai/paper/2006.03654","in_graph_layer":true,"samples":13,"ran":4,"n_ran_checked":3,"n_instrument":1,"unverified":9,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: official). This answer is about arXiv:2006.03654, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"a1b3cbc5195e73e7d1cd3c1ec8f7bb6847c7949efef9bd10ad78d343181b23f1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}