{"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/distilbert/papers/2","list_of":"/method/distilbert","method":"DistilBERT","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":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,166],"of":166,"counts":{"archive_papers_tagged":166,"with_a_code_link":63,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":166,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/distilbert","prev":"/method/distilbert","next":null,"papers":[{"paper":"/paper/a-fast-post-training-pruning-framework-for","slug":"a-fast-post-training-pruning-framework-for","title":"A Fast Post-Training Pruning Framework for Transformers","date":"2022-03-29","arxiv_id":"2204.09656","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["WoosukKwon/retraining-free-pruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/build-a-robust-qa-system-with-transformer","slug":"build-a-robust-qa-system-with-transformer","title":"Build a Robust QA System with Transformer-based Mixture of Experts","date":"2022-03-20","arxiv_id":"2204.09598","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-word-embeddings-to-analyze-protests","title":"Using Word Embeddings to Analyze Protests News","date":"2022-03-11","arxiv_id":"2203.05875","n_code_links":0,"syntology":null},{"paper":"/paper/relationship-extraction-for-knowledge-graph","slug":"relationship-extraction-for-knowledge-graph","title":"Comparison of biomedical relationship extraction methods and models for knowledge graph creation","date":"2022-01-05","arxiv_id":"2201.01647","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-mixed-precision-quantization-search","title":"Automatic Mixed-Precision Quantization Search of BERT","date":"2021-12-30","arxiv_id":"2112.14938","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-scattered-sources-to-comprehensive","title":"From Scattered Sources to Comprehensive Technology Landscape: A Recommendation-based Retrieval Approach","date":"2021-12-09","arxiv_id":"2112.04810","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformers-on-word","title":"A Comparative Study of Transformers on Word Sense Disambiguation","date":"2021-11-30","arxiv_id":"2111.15417","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-coherence-modeling-capabilities","title":"Assessing the Coherence Modeling Capabilities of Pretrained Transformer-based Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","n_code_links":2,"syntology":null},{"paper":null,"slug":"sexism-identification-in-tweets-and-gabs","title":"Sexism Identification in Tweets and Gabs using Deep Neural Networks","date":"2021-11-05","arxiv_id":"2111.03612","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-performance-in-open-domain-dialogue","title":"Modeling Performance in Open-Domain Dialogue with PARADISE","date":"2021-10-21","arxiv_id":"2110.11164","n_code_links":0,"syntology":null},{"paper":null,"slug":"all-in-one-multi-task-learning-bert-models","title":"ALL-IN-ONE: Multi-Task Learning BERT models for Evaluating Peer Assessments","date":"2021-10-08","arxiv_id":"2110.03895","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-transformer-based-sequence-to","title":"Compressing Transformer-Based Sequence to Sequence Models With Pre-trained Autoencoders for Text Summarization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-distillation-using","title":"Cross-Architecture Distillation Using Bidirectional CMOW Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-sentiment-classification-using-0","title":"Improving Sentiment Classification Using 0-Shot Generated Labels for Custom Transformer Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-question-answering-performance","slug":"improving-question-answering-performance","title":"Improving Question Answering Performance Using Knowledge Distillation and Active Learning","date":"2021-09-26","arxiv_id":"2109.12662","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"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":["mirbostani/QA-KD-AL"],"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/new-students-on-sesame-street-what-order","slug":"new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-language-models-for-factoid","slug":"transformer-based-language-models-for-factoid","title":"Transformer-based Language Models for Factoid Question Answering at BioASQ9b","date":"2021-09-15","arxiv_id":"2109.07185","n_code_links":1,"syntology":null},{"paper":"/paper/forget-me-not-a-gentle-reminder-to-mind-the","slug":"forget-me-not-a-gentle-reminder-to-mind-the","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","date":"2021-09-08","arxiv_id":"2109.03777","n_code_links":2,"syntology":null},{"paper":null,"slug":"dkm-differentiable-k-means-clustering-layer","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","date":"2021-08-28","arxiv_id":"2108.12659","n_code_links":0,"syntology":null},{"paper":"/paper/sigmoidf1-a-smooth-f1-score-surrogate-loss","slug":"sigmoidf1-a-smooth-f1-score-surrogate-loss","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","date":"2021-08-24","arxiv_id":"2108.10566","n_code_links":1,"syntology":null},{"paper":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","n_code_links":0,"syntology":null},{"paper":"/paper/attestable-at-semeval-2021-task-9-extending","slug":"attestable-at-semeval-2021-task-9-extending","title":"AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-6","title":"CSECU-DSG at SemEval-2021 Task 6: Orchestrating Multimodal Neural Architectures for Identifying Persuasion Techniques in Texts and Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"uor-at-semeval-2021-task-7-utilizing-pre","title":"UoR at SemEval-2021 Task 7: Utilizing Pre-trained DistilBERT Model and Multi-scale CNN for Humor Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/autotinybert-automatic-hyper-parameter","slug":"autotinybert-automatic-hyper-parameter","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","date":"2021-07-29","arxiv_id":"2107.13686","n_code_links":1,"syntology":null},{"paper":null,"slug":"languagerefer-spatial-language-model-for-3d","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","date":"2021-07-07","arxiv_id":"2107.03438","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":"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":"/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":"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":"/paper/hle-upc-at-semeval-2021-task-5-multi-depth","slug":"hle-upc-at-semeval-2021-task-5-multi-depth","title":"HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection","date":"2021-04-01","arxiv_id":"2104.00639","n_code_links":1,"syntology":null},{"paper":null,"slug":"combat-covid-19-infodemic-using-explainable","title":"Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models","date":"2021-03-01","arxiv_id":"2103.00747","n_code_links":0,"syntology":null},{"paper":"/paper/parallelizing-legendre-memory-unit-training","slug":"parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","arxiv_id":"2102.11417","n_code_links":2,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-federated-learning-for-fine-tuning-of","title":"Scaling Federated Learning for Fine-tuning of Large Language Models","date":"2021-02-01","arxiv_id":"2102.00875","n_code_links":0,"syntology":null},{"paper":null,"slug":"post-training-weighted-quantization-of-neural","title":"Post-Training Weighted Quantization of Neural Networks for Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/yelp-review-rating-prediction-machine","slug":"yelp-review-rating-prediction-machine","title":"Yelp Review Rating Prediction: Machine Learning and Deep Learning Models","date":"2020-12-12","arxiv_id":"2012.06690","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-insincere-questions-from-text-a","slug":"detecting-insincere-questions-from-text-a","title":"Detecting Insincere Questions from Text: A Transfer Learning Approach","date":"2020-12-07","arxiv_id":"2012.07587","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-detection-of-cyberbullying-against","title":"Automated Detection of Cyberbullying Against Women and Immigrants and Cross-domain Adaptability","date":"2020-12-04","arxiv_id":"2012.02565","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-at-semeval-2020-task-8-using-bert-to","title":"BERT at SemEval-2020 Task 8: Using BERT to Analyse Meme Emotions","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/kafk-at-semeval-2020-task-8-extracting","slug":"kafk-at-semeval-2020-task-8-extracting","title":"KAFK at SemEval-2020 Task 8: Extracting Features from Pre-trained Neural Networks to Classify Internet Memes","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-models-for-automatic","title":"Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation","date":"2020-11-26","arxiv_id":"2011.13187","n_code_links":0,"syntology":null},{"paper":"/paper/probing-for-multilingual-numerical","slug":"probing-for-multilingual-numerical","title":"Probing for Multilingual Numerical Understanding in Transformer-Based Language Models","date":"2020-10-13","arxiv_id":"2010.06666","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatbot-interaction-with-artificial","title":"Chatbot Interaction with Artificial Intelligence: Human Data Augmentation with T5 and Language Transformer Ensemble for Text Classification","date":"2020-10-12","arxiv_id":"2010.05990","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-transformer-based-semantic","title":"Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings","date":"2020-10-10","arxiv_id":"2010.05002","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-meets-projective-clustering-1","title":"Deep Learning Meets Projective Clustering","date":"2020-10-08","arxiv_id":"2010.04290","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-transformers-with-approximate-1","slug":"optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","n_code_links":1,"syntology":null},{"paper":"/paper/neural-mask-generator-learning-to-generate","slug":"neural-mask-generator-learning-to-generate","title":"Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation","date":"2020-10-06","arxiv_id":"2010.02705","n_code_links":1,"syntology":null},{"paper":null,"slug":"compositional-and-lexical-semantics-in","title":"Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA","date":"2020-09-17","arxiv_id":"2009.08257","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformer-based-large-scale","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","date":"2020-09-17","arxiv_id":"2009.08065","n_code_links":0,"syntology":null},{"paper":"/paper/compressed-deep-networks-goodbye-svd-hello","slug":"compressed-deep-networks-goodbye-svd-hello","title":"Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation","date":"2020-09-11","arxiv_id":"2009.05647","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-study-of-language-models-on-cross","title":"Comparative Study of Language Models on Cross-Domain Data with Model Agnostic Explainability","date":"2020-09-09","arxiv_id":"2009.04095","n_code_links":0,"syntology":null},{"paper":"/paper/sentimental-liar-extended-corpus-and-deep","slug":"sentimental-liar-extended-corpus-and-deep","title":"Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification","date":"2020-09-01","arxiv_id":"2009.01047","n_code_links":2,"syntology":null},{"paper":"/paper/top2vec-distributed-representations-of-topics","slug":"top2vec-distributed-representations-of-topics","title":"Top2Vec: Distributed Representations of Topics","date":"2020-08-19","arxiv_id":"2008.09470","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ddangelov/Top2Vec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cooking-is-all-about-people-comment","title":"Cooking Is All About People: Comment Classification On Cookery Channels Using BERT and Classification Models (Malayalam-English Mix-Code)","date":"2020-06-15","arxiv_id":"2007.04249","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-natural-language-understanding","slug":"accelerating-natural-language-understanding","title":"Accelerating Natural Language Understanding in Task-Oriented Dialog","date":"2020-06-05","arxiv_id":"2006.03701","n_code_links":1,"syntology":null},{"paper":null,"slug":"lrg-at-semeval-2020-task-7-assessing-the","title":"LRG at SemEval-2020 Task 7: Assessing the Ability of BERT and Derivative Models to Perform Short-Edits based Humor Grading","date":"2020-05-31","arxiv_id":"2006.00607","n_code_links":0,"syntology":null},{"paper":"/paper/language-representation-models-for-fine","slug":"language-representation-models-for-fine","title":"Language Representation Models for Fine-Grained Sentiment Classification","date":"2020-05-27","arxiv_id":"2005.13619","n_code_links":1,"syntology":null},{"paper":"/paper/establishing-baselines-for-text","slug":"establishing-baselines-for-text","title":"Establishing Baselines for Text Classification in Low-Resource Languages","date":"2020-05-05","arxiv_id":"2005.02068","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-elmo-and-distilbert-on-socio","title":"Analyzing ELMo and DistilBERT on Socio-political News Classification","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/poor-man-s-bert-smaller-and-faster","slug":"poor-man-s-bert-smaller-and-faster","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","date":"2020-04-08","arxiv_id":"2004.03844","n_code_links":4,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hsajjad/transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"improved-pretraining-for-domain-specific","title":"Continual Domain-Tuning for Pretrained Language Models","date":"2020-04-05","arxiv_id":"2004.02288","n_code_links":0,"syntology":null},{"paper":"/paper/deep-entity-matching-with-pre-trained","slug":"deep-entity-matching-with-pre-trained","title":"Deep Entity Matching with Pre-Trained Language Models","date":"2020-04-01","arxiv_id":"2004.00584","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["megagonlabs/ditto"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","n_code_links":37,"syntology":{"ran":21,"of":27,"n_ran_checked":13,"n_instrument":8,"unverified":6,"pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"fb23f068cd0450b29940245d49ba1f88297064e80a4ade24379f8c24ca3e02bb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}