{"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/weight-decay/papers/64","list_of":"/method/weight-decay","method":"Weight 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":64,"pages_in_order":108,"rows_per_page":100,"rows":[6301,6400],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/63","next":"/method/weight-decay/papers/65","papers":[{"paper":"/paper/domain-adaptive-text-classification-with","slug":"domain-adaptive-text-classification-with","title":"Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data","date":"2022-06-20","arxiv_id":"2206.09591","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["hikaru-nara/dask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/nuqmm-quantized-matmul-for-efficient","slug":"nuqmm-quantized-matmul-for-efficient","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","date":"2022-06-20","arxiv_id":"2206.09557","n_code_links":2,"syntology":null},{"paper":null,"slug":"when-does-re-initialization-work","title":"When Does Re-initialization Work?","date":"2022-06-20","arxiv_id":"2206.10011","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-hop-age-of-information-scheduling-for","title":"Two-Hop Age of Information Scheduling for Multi-UAV Assisted Mobile Edge Computing: FRL vs MADDPG","date":"2022-06-19","arxiv_id":"2206.09488","n_code_links":0,"syntology":null},{"paper":"/paper/argumentative-text-generation-in-economic","slug":"argumentative-text-generation-in-economic","title":"Argumentative Text Generation in Economic Domain","date":"2022-06-18","arxiv_id":"2206.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-russian-texts","title":"Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods","date":"2022-06-18","arxiv_id":"2206.09253","n_code_links":0,"syntology":null},{"paper":null,"slug":"ruarg-2022-argument-mining-evaluation","title":"RuArg-2022: Argument Mining Evaluation","date":"2022-06-18","arxiv_id":"2206.09249","n_code_links":0,"syntology":null},{"paper":null,"slug":"bits-pilani-at-hinglisheval-quality","title":"BITS Pilani at HinglishEval: Quality Evaluation for Code-Mixed Hinglish Text Using Transformers","date":"2022-06-17","arxiv_id":"2206.08680","n_code_links":0,"syntology":null},{"paper":"/paper/video-sparse-transformer-with-attention","slug":"video-sparse-transformer-with-attention","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","date":"2022-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"an-open-domain-qa-system-for-e-governance","title":"An Open-Domain QA System for e-Governance","date":"2022-06-16","arxiv_id":"2206.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"autonomous-platoon-control-with-integrated","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","date":"2022-06-15","arxiv_id":"2206.07536","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-harmful-online-conversational","slug":"detecting-harmful-online-conversational","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","date":"2022-06-15","arxiv_id":"2207.10032","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-confidence-of-predictions-of","title":"Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task","date":"2022-06-15","arxiv_id":"2206.07427","n_code_links":0,"syntology":null},{"paper":null,"slug":"rdu-a-region-based-approach-to-form-style","title":"RDU: A Region-based Approach to Form-style Document Understanding","date":"2022-06-14","arxiv_id":"2206.06890","n_code_links":0,"syntology":null},{"paper":"/paper/sbert-studies-meaning-representations","slug":"sbert-studies-meaning-representations","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","date":"2022-06-14","arxiv_id":"2206.07023","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["flipz357/S3BERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"computation-offloading-and-resource-1","title":"Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach","date":"2022-06-13","arxiv_id":"2206.05881","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-clipping-and-magnitude-aware","slug":"optimal-clipping-and-magnitude-aware","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","date":"2022-06-13","arxiv_id":"2206.06501","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"transition-based-abstract-meaning","title":"Transition-based Abstract Meaning Representation Parsing with Contextual Embeddings","date":"2022-06-13","arxiv_id":"2206.06229","n_code_links":0,"syntology":null},{"paper":null,"slug":"sgd-noise-and-implicit-low-rank-bias-in-deep","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","date":"2022-06-12","arxiv_id":"2206.05794","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dataset-and-benchmark-for-automatically","title":"From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams","date":"2022-06-11","arxiv_id":"2206.05442","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-snippet-generation-1","slug":"comparative-snippet-generation-1","title":"Comparative Snippet Generation","date":"2022-06-11","arxiv_id":"2206.05473","n_code_links":1,"syntology":null},{"paper":"/paper/putting-gpt-3-s-creativity-to-the-alternative","slug":"putting-gpt-3-s-creativity-to-the-alternative","title":"Putting GPT-3's Creativity to the (Alternative Uses) Test","date":"2022-06-10","arxiv_id":"2206.08932","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-the-imitation-game-quantifying-and","slug":"beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","n_code_links":6,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google/BIG-bench"],"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":"joint-encoder-decoder-self-supervised-pre","title":"Joint Encoder-Decoder Self-Supervised Pre-training for ASR","date":"2022-06-09","arxiv_id":"2206.04465","n_code_links":0,"syntology":null},{"paper":"/paper/traditional-and-context-specific-spam","slug":"traditional-and-context-specific-spam","title":"Traditional and context-specific spam detection in low resource settings","date":"2022-06-09","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/abstraction-not-memory-bert-and-the-english","slug":"abstraction-not-memory-bert-and-the-english","title":"Abstraction not Memory: BERT and the English Article System","date":"2022-06-08","arxiv_id":"2206.04184","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":"/paper/always-keep-your-target-in-mind-studying-1","slug":"always-keep-your-target-in-mind-studying-1","title":"Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution","date":"2022-06-07","arxiv_id":"2206.11815","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-iot-security-aspects-at","title":"An Empirical Study of IoT Security Aspects at Sentence-Level in Developer Textual Discussions","date":"2022-06-07","arxiv_id":"2206.03079","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamar-dynamic-prompt-with-mask-token","title":"DynaMaR: Dynamic Prompt with Mask Token Representation","date":"2022-06-07","arxiv_id":"2206.02982","n_code_links":0,"syntology":null},{"paper":null,"slug":"ochadai-at-semeval-2022-task-2-adversarial","title":"OCHADAI at SemEval-2022 Task 2: Adversarial Training for Multilingual Idiomaticity Detection","date":"2022-06-07","arxiv_id":"2206.03025","n_code_links":0,"syntology":null},{"paper":"/paper/a-computational-psycholinguistic-evaluation","slug":"a-computational-psycholinguistic-evaluation","title":"A computational psycholinguistic evaluation of the syntactic abilities of Galician BERT models at the interface of dependency resolution and training time","date":"2022-06-06","arxiv_id":"2206.02440","n_code_links":1,"syntology":null},{"paper":null,"slug":"balancing-profit-risk-and-sustainability-for","title":"Balancing Profit, Risk, and Sustainability for Portfolio Management","date":"2022-06-06","arxiv_id":"2207.02134","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-advance-of-making-language-models","slug":"on-the-advance-of-making-language-models","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","date":"2022-06-06","arxiv_id":"2206.02336","n_code_links":0,"syntology":null},{"paper":null,"slug":"spam-detection-using-bert","title":"Spam Detection Using BERT","date":"2022-06-06","arxiv_id":"2206.02443","n_code_links":0,"syntology":null},{"paper":"/paper/what-do-tokens-know-about-their-characters-1","slug":"what-do-tokens-know-about-their-characters-1","title":"What do tokens know about their characters and how do they know it?","date":"2022-06-06","arxiv_id":"2206.02608","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-online-travel-reviews","title":"Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon","date":"2022-06-05","arxiv_id":"2206.02160","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-detection-task-against-asian-hate-bert","title":"Speech Detection Task Against Asian Hate: BERT the Central, While Data-Centric Studies the Crucial","date":"2022-06-05","arxiv_id":"2206.02114","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-performance-of-different","title":"Comparing Performance of Different Linguistically-Backed Word Embeddings for Cyberbullying Detection","date":"2022-06-04","arxiv_id":"2206.01950","n_code_links":0,"syntology":null},{"paper":"/paper/extreme-compression-for-pre-trained","slug":"extreme-compression-for-pre-trained","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","date":"2022-06-04","arxiv_id":"2206.01859","n_code_links":1,"syntology":null},{"paper":"/paper/zeroquant-efficient-and-affordable-post","slug":"zeroquant-efficient-and-affordable-post","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","date":"2022-06-04","arxiv_id":"2206.01861","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/DeepSpeed"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"automatic-generation-of-programming-exercises-1","title":"Automatic Generation of Programming Exercises and Code Explanations using Large Language Models","date":"2022-06-03","arxiv_id":"2206.11861","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentially-private-model-compression","title":"Differentially Private Model Compression","date":"2022-06-03","arxiv_id":"2206.01838","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-similar-questions-from-naturally","title":"Extracting Similar Questions From Naturally-occurring Business Conversations","date":"2022-06-03","arxiv_id":"2206.01585","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-energy-dispatch-and-unit-commitment-in","title":"Joint Energy Dispatch and Unit Commitment in Microgrids Based on Deep Reinforcement Learning","date":"2022-06-03","arxiv_id":"2206.01663","n_code_links":0,"syntology":null},{"paper":"/paper/tce-at-qur-an-qa-2022-arabic-language","slug":"tce-at-qur-an-qa-2022-arabic-language","title":"TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models","date":"2022-06-03","arxiv_id":"2206.01550","n_code_links":1,"syntology":null},{"paper":"/paper/decentralized-training-of-foundation-models","slug":"decentralized-training-of-foundation-models","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","date":"2022-06-02","arxiv_id":"2206.01288","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["DS3Lab/DT-FM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mmtm-multi-tasking-multi-decoder-transformer","title":"MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems","date":"2022-06-02","arxiv_id":"2206.01268","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-group-level-gender-bias-in","title":"Assessing Group-level Gender Bias in Professional Evaluations: The Case of Medical Student End-of-Shift Feedback","date":"2022-06-01","arxiv_id":"2206.00234","n_code_links":0,"syntology":null},{"paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","slug":"bert-sort-a-zero-shot-mlm-semantic-encoder-on","title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"order-sensitive-shapley-values-for-evaluating","title":"Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models","date":"2022-06-01","arxiv_id":"2206.00192","n_code_links":0,"syntology":null},{"paper":null,"slug":"romantic-computing","title":"Romantic-Computing","date":"2022-06-01","arxiv_id":"2206.11864","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-framework-for-emotion","title":"A Unified Framework for Emotion Identification and Generation in Dialogues","date":"2022-05-31","arxiv_id":"2205.15513","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-deep-learning-a-case-study-in","title":"Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain","date":"2022-05-31","arxiv_id":"2205.15952","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-short-math-answer-grading-via-in","slug":"automatic-short-math-answer-grading-via-in","title":"Automatic Short Math Answer Grading via In-context Meta-learning","date":"2022-05-30","arxiv_id":"2205.15219","n_code_links":1,"syntology":null},{"paper":"/paper/billions-of-parameters-are-worth-more-than-in","slug":"billions-of-parameters-are-worth-more-than-in","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","date":"2022-05-30","arxiv_id":"2205.15172","n_code_links":1,"syntology":null},{"paper":"/paper/multi-agent-reinforcement-learning-is-a","slug":"multi-agent-reinforcement-learning-is-a","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","date":"2022-05-30","arxiv_id":"2205.14953","n_code_links":1,"syntology":null},{"paper":"/paper/prompting-electra-few-shot-learning-with","slug":"prompting-electra-few-shot-learning-with","title":"Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models","date":"2022-05-30","arxiv_id":"2205.15223","n_code_links":1,"syntology":null},{"paper":"/paper/truly-deterministic-policy-optimization-1","slug":"truly-deterministic-policy-optimization-1","title":"Truly Deterministic Policy Optimization","date":"2022-05-30","arxiv_id":"2205.15379","n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-literature-mining-and-retrieval","title":"COVID-19 Literature Mining and Retrieval using Text Mining Approaches","date":"2022-05-29","arxiv_id":"2205.14781","n_code_links":0,"syntology":null},{"paper":"/paper/cped-a-large-scale-chinese-personalized-and-1","slug":"cped-a-large-scale-chinese-personalized-and-1","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","date":"2022-05-29","arxiv_id":"2205.14727","n_code_links":1,"syntology":null},{"paper":null,"slug":"micro-expression-recognition-based-on","title":"Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning","date":"2022-05-29","arxiv_id":"2205.14643","n_code_links":0,"syntology":null},{"paper":null,"slug":"urdu-news-article-recommendation-model-using","title":"Urdu News Article Recommendation Model using Natural Language Processing Techniques","date":"2022-05-29","arxiv_id":"2206.11862","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-models-to-express-their-uncertainty","slug":"teaching-models-to-express-their-uncertainty","title":"Teaching Models to Express Their Uncertainty in Words","date":"2022-05-28","arxiv_id":"2205.14334","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: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sylinrl/calibratedmath"],"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":"/paper/flashattention-fast-and-memory-efficient","slug":"flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","arxiv_id":"2205.14135","n_code_links":13,"syntology":{"ran":24,"of":30,"n_ran_checked":18,"n_instrument":6,"unverified":6,"pointer_only":1,"phrase":"24 ran (of which 2 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["dao-ailab/flash-attention"],"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":["found_in_text","listed"]}}},{"paper":"/paper/multimodal-masked-autoencoders-learn","slug":"multimodal-masked-autoencoders-learn","title":"Multimodal Masked Autoencoders Learn Transferable Representations","date":"2022-05-27","arxiv_id":"2205.14204","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":9,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"12 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["young-geng/m3ae_public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/nearest-neighbor-zero-shot-inference","slug":"nearest-neighbor-zero-shot-inference","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","date":"2022-05-27","arxiv_id":"2205.13792","n_code_links":1,"syntology":null},{"paper":"/paper/what-dense-graph-do-you-need-for-self","slug":"what-dense-graph-do-you-need-for-self","title":"What Dense Graph Do You Need for Self-Attention?","date":"2022-05-27","arxiv_id":"2205.14014","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-split-bert-for-heterogeneous-text","title":"Federated Split BERT for Heterogeneous Text Classification","date":"2022-05-26","arxiv_id":"2205.13299","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-dependency-grammar-for-fine","slug":"leveraging-dependency-grammar-for-fine","title":"Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks","date":"2022-05-26","arxiv_id":"2205.13164","n_code_links":1,"syntology":null},{"paper":"/paper/the-document-vectors-using-cosine-similarity-1","slug":"the-document-vectors-using-cosine-similarity-1","title":"The Document Vectors Using Cosine Similarity Revisited","date":"2022-05-26","arxiv_id":"2205.13357","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-inference-on-any-order","slug":"training-and-inference-on-any-order","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","date":"2022-05-26","arxiv_id":"2205.13554","n_code_links":1,"syntology":null},{"paper":"/paper/bit-robustly-binarized-multi-distilled","slug":"bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","arxiv_id":"2205.13016","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/bit"],"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":["listed","official"]}}},{"paper":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-zero-shot-clinical","title":"Large Language Models are Few-Shot Clinical Information Extractors","date":"2022-05-25","arxiv_id":"2205.12689","n_code_links":0,"syntology":null},{"paper":null,"slug":"lifelong-learning-natural-language-processing","title":"Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification","date":"2022-05-25","arxiv_id":"2206.11867","n_code_links":0,"syntology":null},{"paper":"/paper/naturalprover-grounded-mathematical-proof","slug":"naturalprover-grounded-mathematical-proof","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","date":"2022-05-25","arxiv_id":"2205.12910","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":["wellecks/naturalprover"],"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":null,"slug":"orca-interpreting-prompted-language-models","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","date":"2022-05-25","arxiv_id":"2205.12600","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-to-face-generation-with-stylegan2","title":"Text-to-Face Generation with StyleGAN2","date":"2022-05-25","arxiv_id":"2205.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-label-regularization","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","date":"2022-05-25","arxiv_id":"2205.12428","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-flat-then-compress-sharpness-aware","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","date":"2022-05-25","arxiv_id":"2205.12694","n_code_links":0,"syntology":null},{"paper":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","n_code_links":1,"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":null}},{"paper":"/paper/vulberta-simplified-source-code-pre-training","slug":"vulberta-simplified-source-code-pre-training","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","date":"2022-05-25","arxiv_id":"2205.12424","n_code_links":1,"syntology":null},{"paper":"/paper/flute-figurative-language-understanding-and","slug":"flute-figurative-language-understanding-and","title":"FLUTE: Figurative Language Understanding through Textual Explanations","date":"2022-05-24","arxiv_id":"2205.12404","n_code_links":1,"syntology":null},{"paper":"/paper/formulating-few-shot-fine-tuning-towards","slug":"formulating-few-shot-fine-tuning-towards","title":"Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition","date":"2022-05-24","arxiv_id":"2205.11799","n_code_links":1,"syntology":null},{"paper":"/paper/garden-path-traversal-within-gpt-2","slug":"garden-path-traversal-within-gpt-2","title":"Garden-Path Traversal in GPT-2","date":"2022-05-24","arxiv_id":"2205.12302","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wjurayj/garden-path-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-human-is-human-evaluation-improving-the","title":"The Authenticity Gap in Human Evaluation","date":"2022-05-24","arxiv_id":"2205.11930","n_code_links":0,"syntology":null},{"paper":"/paper/k-12bert-bert-for-k-12-education","slug":"k-12bert-bert-for-k-12-education","title":"K-12BERT: BERT for K-12 education","date":"2022-05-24","arxiv_id":"2205.12335","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-role-of-bidirectionality-in-language","title":"On the Role of Bidirectionality in Language Model Pre-Training","date":"2022-05-24","arxiv_id":"2205.11726","n_code_links":0,"syntology":null},{"paper":"/paper/partial-input-baselines-show-that-nli-models","slug":"partial-input-baselines-show-that-nli-models","title":"Partial-input baselines show that NLI models can ignore context, but they don't","date":"2022-05-24","arxiv_id":"2205.12181","n_code_links":1,"syntology":null},{"paper":"/paper/retromae-pre-training-retrieval-oriented","slug":"retromae-pre-training-retrieval-oriented","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","date":"2022-05-24","arxiv_id":"2205.12035","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-mixers-combining-moe-and-mixing-to","slug":"sparse-mixers-combining-moe-and-mixing-to","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","date":"2022-05-24","arxiv_id":"2205.12399","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-order-typology-in-multilingual-bert-a","title":"Word-order typology in Multilingual BERT: A case study in subordinate-clause detection","date":"2022-05-24","arxiv_id":"2205.11987","n_code_links":0,"syntology":null},{"paper":"/paper/artificial-intelligence-for-topic-modelling","slug":"artificial-intelligence-for-topic-modelling","title":"Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita","date":"2022-05-23","arxiv_id":"2205.11020","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-short-text-classification-with","title":"Improving Short Text Classification With Augmented Data Using GPT-3","date":"2022-05-23","arxiv_id":"2205.10981","n_code_links":0,"syntology":null},{"paper":"/paper/kold-korean-offensive-language-dataset","slug":"kold-korean-offensive-language-dataset","title":"KOLD: Korean Offensive Language Dataset","date":"2022-05-23","arxiv_id":"2205.11315","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-ignore-adversarial-attacks-1","title":"Learning to Ignore Adversarial Attacks","date":"2022-05-23","arxiv_id":"2205.11551","n_code_links":0,"syntology":null},{"paper":"/paper/looking-for-a-handsome-carpenter-debiasing","slug":"looking-for-a-handsome-carpenter-debiasing","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","date":"2022-05-23","arxiv_id":"2205.11374","n_code_links":1,"syntology":null}],"record_sha256":"b81392ebb36bc6ffe6ae129a7ee27162c622cde3b028e49a6e4fe0b42775a0b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}