{"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/59","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":59,"pages_in_order":108,"rows_per_page":100,"rows":[5801,5900],"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/58","next":"/method/weight-decay/papers/60","papers":[{"paper":"/paper/luna-language-understanding-with-number","slug":"luna-language-understanding-with-number","title":"LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training","date":"2022-12-06","arxiv_id":"2212.02691","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zmy/luna"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"modern-french-poetry-generation-with-roberta","title":"Modern French Poetry Generation with RoBERTa and GPT-2","date":"2022-12-06","arxiv_id":"2212.02911","n_code_links":0,"syntology":null},{"paper":null,"slug":"style-transfer-and-classification-in-hebrew","title":"Style transfer and classification in hebrew news items","date":"2022-12-06","arxiv_id":"2212.03019","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-driven-co-speech-gesture-video","title":"Audio-Driven Co-Speech Gesture Video Generation","date":"2022-12-05","arxiv_id":"2212.02350","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-factual-news","title":"Automatic Generation of Factual News Headlines in Finnish","date":"2022-12-05","arxiv_id":"2212.02170","n_code_links":0,"syntology":null},{"paper":"/paper/video-games-as-a-corpus-sentiment-analysis","slug":"video-games-as-a-corpus-sentiment-analysis","title":"Video Games as a Corpus: Sentiment Analysis using Fallout New Vegas Dialog","date":"2022-12-05","arxiv_id":"2212.02168","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-differentially","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","date":"2022-12-03","arxiv_id":"2212.01539","n_code_links":0,"syntology":null},{"paper":null,"slug":"cold-fusion-collaborative-descent-for","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","date":"2022-12-02","arxiv_id":"2212.01378","n_code_links":0,"syntology":null},{"paper":"/paper/event-knowledge-in-large-language-models-the","slug":"event-knowledge-in-large-language-models-the","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","date":"2022-12-02","arxiv_id":"2212.01488","n_code_links":1,"syntology":null},{"paper":"/paper/sumren-summarizing-reported-speech-about","slug":"sumren-summarizing-reported-speech-about","title":"SumREN: Summarizing Reported Speech about Events in News","date":"2022-12-02","arxiv_id":"2212.01146","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-gpt-3","title":"a survey on GPT-3","date":"2022-12-01","arxiv_id":"2212.00857","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapted-multimodal-bert-with-layer-wise","title":"Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis","date":"2022-12-01","arxiv_id":"2212.00678","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-multi-step-reasoning-capabilities","slug":"distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","n_code_links":1,"syntology":null},{"paper":null,"slug":"budgetlongformer-can-we-cheaply-pretrain-a","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","date":"2022-11-30","arxiv_id":"2211.17135","n_code_links":0,"syntology":null},{"paper":"/paper/extremebert-a-toolkit-for-accelerating","slug":"extremebert-a-toolkit-for-accelerating","title":"ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT","date":"2022-11-30","arxiv_id":"2211.17201","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["extreme-bert/extreme-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"heat-hardware-efficient-automatic-tensor","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","date":"2022-11-30","arxiv_id":"2211.16749","n_code_links":0,"syntology":null},{"paper":null,"slug":"quadapter-adapter-for-gpt-2-quantization","title":"Quadapter: Adapter for GPT-2 Quantization","date":"2022-11-30","arxiv_id":"2211.16912","n_code_links":0,"syntology":null},{"paper":"/paper/composition-based-oxidation-state-prediction","slug":"composition-based-oxidation-state-prediction","title":"Composition based oxidation state prediction of materials using deep learning","date":"2022-11-29","arxiv_id":"2211.15895","n_code_links":1,"syntology":null},{"paper":null,"slug":"diverse-multi-answer-retrieval-with-1","title":"Diverse Multi-Answer Retrieval with Determinantal Point Processes","date":"2022-11-29","arxiv_id":"2211.16029","n_code_links":0,"syntology":null},{"paper":null,"slug":"outfit-generation-and-recommendation-an","title":"Outfit Generation and Recommendation -- An Experimental Study","date":"2022-11-29","arxiv_id":"2211.16353","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-opinion-summarization-with-gpt-3","slug":"zero-shot-opinion-summarization-with-gpt-3","title":"Prompted Opinion Summarization with GPT-3.5","date":"2022-11-29","arxiv_id":"2211.15914","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatically-extracting-information-in","title":"Automatically Extracting Information in Medical Dialogue: Expert System And Attention for Labelling","date":"2022-11-28","arxiv_id":"2211.15544","n_code_links":0,"syntology":null},{"paper":"/paper/diffusionbert-improving-generative-masked","slug":"diffusionbert-improving-generative-masked","title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","date":"2022-11-28","arxiv_id":"2211.15029","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hzfinfdu/diffusion-bert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-neo-for-commonsense-reasoning-a","slug":"gpt-neo-for-commonsense-reasoning-a","title":"GPT-Neo for commonsense reasoning -- a theoretical and practical lens","date":"2022-11-28","arxiv_id":"2211.15593","n_code_links":1,"syntology":null},{"paper":null,"slug":"handling-and-extracting-key-entities-from","title":"Handling and extracting key entities from customer conversations using Speech recognition and Named Entity recognition","date":"2022-11-28","arxiv_id":"2211.17107","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-it-required-ranking-the-skills-required","title":"Is it Required? Ranking the Skills Required for a Job-Title","date":"2022-11-28","arxiv_id":"2212.08553","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-distance-metric-learning-for-few","title":"Revisiting Distance Metric Learning for Few-Shot Natural Language Classification","date":"2022-11-28","arxiv_id":"2211.15202","n_code_links":0,"syntology":null},{"paper":"/paper/scientific-and-creative-analogies-in","slug":"scientific-and-creative-analogies-in","title":"Scientific and Creative Analogies in Pretrained Language Models","date":"2022-11-28","arxiv_id":"2211.15268","n_code_links":2,"syntology":null},{"paper":null,"slug":"awte-bert-attending-to-wordpiece-tokenization","title":"ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling","date":"2022-11-27","arxiv_id":"2211.14829","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-bloom-an-empirical-study-on","title":"Understanding BLOOM: An empirical study on diverse NLP tasks","date":"2022-11-27","arxiv_id":"2211.14865","n_code_links":0,"syntology":null},{"paper":"/paper/an-analysis-of-social-biases-present-in-bert","slug":"an-analysis-of-social-biases-present-in-bert","title":"An Analysis of Social Biases Present in BERT Variants Across Multiple Languages","date":"2022-11-25","arxiv_id":"2211.14402","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["parishadbehnam/social-biases-in-bert-variants-across-multiple-languages"],"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":"/paper/finetuning-bert-on-partially-annotated-ner","slug":"finetuning-bert-on-partially-annotated-ner","title":"Finetuning BERT on Partially Annotated NER Corpora","date":"2022-11-25","arxiv_id":"2211.14360","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-3-driven-pedagogical-agents-for-training","title":"GPT-3-driven pedagogical agents for training children's curious question-asking skills","date":"2022-11-25","arxiv_id":"2211.14228","n_code_links":0,"syntology":null},{"paper":null,"slug":"index-indonesian-idiom-and-expression-dataset","title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test","date":"2022-11-24","arxiv_id":"2211.13376","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-selective-masking-as-a-bridge-between","title":"Using Selective Masking as a Bridge between Pre-training and Fine-tuning","date":"2022-11-24","arxiv_id":"2211.13815","n_code_links":0,"syntology":null},{"paper":"/paper/improving-visual-textual-sentiment-analysis","slug":"improving-visual-textual-sentiment-analysis","title":"Holistic Visual-Textual Sentiment Analysis with Prior Models","date":"2022-11-23","arxiv_id":"2211.12981","n_code_links":1,"syntology":null},{"paper":null,"slug":"seat-stable-and-explainable-attention","title":"SEAT: Stable and Explainable Attention","date":"2022-11-23","arxiv_id":"2211.13290","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-level-representation-from-bytes-for","title":"Word-Level Representation From Bytes For Language Modeling","date":"2022-11-23","arxiv_id":"2211.12677","n_code_links":0,"syntology":null},{"paper":null,"slug":"olga-an-ontology-and-lstm-based-approach-for","title":"OLGA : An Ontology and LSTM-based approach for generating Arithmetic Word Problems (AWPs) of transfer type","date":"2022-11-22","arxiv_id":"2211.12164","n_code_links":0,"syntology":null},{"paper":"/paper/prompttts-controllable-text-to-speech-with","slug":"prompttts-controllable-text-to-speech-with","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","date":"2022-11-22","arxiv_id":"2211.12171","n_code_links":1,"syntology":null},{"paper":"/paper/cbeaf-adapting-enhanced-continual-pretraining","slug":"cbeaf-adapting-enhanced-continual-pretraining","title":"AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model","date":"2022-11-21","arxiv_id":"2211.11363","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-efficacy-of-pre-trained","slug":"exploring-the-efficacy-of-pre-trained","title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","date":"2022-11-21","arxiv_id":"2211.11216","n_code_links":2,"syntology":null},{"paper":null,"slug":"l3cube-hindbert-and-devbert-pre-trained-bert","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","date":"2022-11-21","arxiv_id":"2211.11418","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahasbert-and-hindsbert-sentence-bert","slug":"l3cube-mahasbert-and-hindsbert-sentence-bert","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","date":"2022-11-21","arxiv_id":"2211.11187","n_code_links":1,"syntology":null},{"paper":"/paper/language-in-a-bottle-language-model-guided","slug":"language-in-a-bottle-language-model-guided","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","date":"2022-11-21","arxiv_id":"2211.11158","n_code_links":2,"syntology":null},{"paper":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","slug":"pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yangyangyang127/pointclip_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tcbert-a-technical-report-for-chinese-topic","title":"TCBERT: A Technical Report for Chinese Topic Classification BERT","date":"2022-11-21","arxiv_id":"2211.11304","n_code_links":0,"syntology":null},{"paper":null,"slug":"conceptor-aided-debiasing-of-contextualized","title":"Conceptor-Aided Debiasing of Large Language Models","date":"2022-11-20","arxiv_id":"2211.11087","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-conspiracy-theory-against-covid-19","title":"Detecting Conspiracy Theory Against COVID-19 Vaccines","date":"2022-11-20","arxiv_id":"2211.13003","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-weaken-vicinal-data-augmentation-for","title":"Feature Weaken: Vicinal Data Augmentation for Classification","date":"2022-11-20","arxiv_id":"2211.10944","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-and-improving-knowledge-1","slug":"understanding-and-improving-knowledge-1","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","date":"2022-11-20","arxiv_id":"2211.11014","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","n_code_links":0,"syntology":null},{"paper":null,"slug":"entity-assisted-language-models-for","title":"Entity-Assisted Language Models for Identifying Check-worthy Sentences","date":"2022-11-19","arxiv_id":"2211.10678","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-users-social-network-embeddings","title":"Leveraging Users' Social Network Embeddings for Fake News Detection on Twitter","date":"2022-11-19","arxiv_id":"2211.10672","n_code_links":0,"syntology":null},{"paper":null,"slug":"metadata-might-make-language-models-better","title":"Metadata Might Make Language Models Better","date":"2022-11-18","arxiv_id":"2211.10086","n_code_links":0,"syntology":null},{"paper":null,"slug":"where-did-you-tweet-from-inferring-the-origin","title":"Where did you tweet from? Inferring the origin locations of tweets based on contextual information","date":"2022-11-18","arxiv_id":"2211.16506","n_code_links":0,"syntology":null},{"paper":"/paper/ignore-previous-prompt-attack-techniques-for","slug":"ignore-previous-prompt-attack-techniques-for","title":"Ignore Previous Prompt: Attack Techniques For Language Models","date":"2022-11-17","arxiv_id":"2211.09527","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["agencyenterprise/promptinject"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"longfnt-long-form-speech-recognition-with","title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer","date":"2022-11-17","arxiv_id":"2211.09412","n_code_links":0,"syntology":null},{"paper":"/paper/protsi-prototypical-siamese-network-with-data","slug":"protsi-prototypical-siamese-network-with-data","title":"ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation","date":"2022-11-17","arxiv_id":"2211.09855","n_code_links":1,"syntology":null},{"paper":"/paper/random-ltd-random-and-layerwise-token","slug":"random-ltd-random-and-layerwise-token","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","date":"2022-11-17","arxiv_id":"2211.11586","n_code_links":1,"syntology":null},{"paper":"/paper/unisumm-unified-few-shot-summarization-with","slug":"unisumm-unified-few-shot-summarization-with","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","date":"2022-11-17","arxiv_id":"2211.09783","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-and-accurate-fsa-system-using-elbert-an","title":"Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT","date":"2022-11-16","arxiv_id":"2211.08842","n_code_links":0,"syntology":null},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tsmind-alibaba-and-soochow-university-s","title":"TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task","date":"2022-11-16","arxiv_id":"2211.08987","n_code_links":0,"syntology":null},{"paper":"/paper/an-fnet-based-auto-encoder-for-long-sequence","slug":"an-fnet-based-auto-encoder-for-long-sequence","title":"An FNet based Auto Encoder for Long Sequence News Story Generation","date":"2022-11-15","arxiv_id":"2211.08295","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-language-models-with-knowledge","title":"Empowering Language Models with Knowledge Graph Reasoning for Question Answering","date":"2022-11-15","arxiv_id":"2211.08380","n_code_links":0,"syntology":null},{"paper":"/paper/glue-x-evaluating-natural-language","slug":"glue-x-evaluating-natural-language","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","date":"2022-11-15","arxiv_id":"2211.08073","n_code_links":1,"syntology":null},{"paper":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","n_code_links":1,"syntology":null},{"paper":null,"slug":"robbert-2022-updating-a-dutch-language-model","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","date":"2022-11-15","arxiv_id":"2211.08192","n_code_links":0,"syntology":null},{"paper":"/paper/are-hard-examples-also-harder-to-explain-a","slug":"are-hard-examples-also-harder-to-explain-a","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","date":"2022-11-14","arxiv_id":"2211.07517","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["swarnahub/explanationhardness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ugif-ui-grounded-instruction-following","slug":"ugif-ui-grounded-instruction-following","title":"UGIF: UI Grounded Instruction Following","date":"2022-11-14","arxiv_id":"2211.07615","n_code_links":0,"syntology":null},{"paper":"/paper/greenplm-cross-lingual-pre-trained-language","slug":"greenplm-cross-lingual-pre-trained-language","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","date":"2022-11-13","arxiv_id":"2211.06993","n_code_links":1,"syntology":null},{"paper":null,"slug":"textual-data-augmentation-for-patient","title":"Textual Data Augmentation for Patient Outcomes Prediction","date":"2022-11-13","arxiv_id":"2211.06778","n_code_links":0,"syntology":null},{"paper":"/paper/what-would-harry-say-building-dialogue-agents","slug":"what-would-harry-say-building-dialogue-agents","title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","date":"2022-11-13","arxiv_id":"2211.06869","n_code_links":1,"syntology":null},{"paper":"/paper/xu-at-semeval-2022-task-4-pre-bert-neural-1","slug":"xu-at-semeval-2022-task-4-pre-bert-neural-1","title":"Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detection","date":"2022-11-13","arxiv_id":"2211.06874","n_code_links":1,"syntology":null},{"paper":null,"slug":"cacto-continuous-actor-critic-with-trajectory","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","date":"2022-11-12","arxiv_id":"2211.06625","n_code_links":0,"syntology":null},{"paper":"/paper/dark-patterns-in-e-commerce-a-dataset-and-its","slug":"dark-patterns-in-e-commerce-a-dataset-and-its","title":"Dark patterns in e-commerce: a dataset and its baseline evaluations","date":"2022-11-12","arxiv_id":"2211.06543","n_code_links":1,"syntology":null},{"paper":"/paper/misinformation-detection-using-persuasive","slug":"misinformation-detection-using-persuasive","title":"Using Persuasive Writing Strategies to Explain and Detect Health Misinformation","date":"2022-11-11","arxiv_id":"2211.05985","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-combination-of-convolutional-and","title":"BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05273","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-in-plutarch-s-shadows","title":"BERT in Plutarch's Shadows","date":"2022-11-10","arxiv_id":"2211.05673","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-multi-hop-question-answering-using","title":"Biomedical Multi-hop Question Answering Using Knowledge Graph Embeddings and Language Models","date":"2022-11-10","arxiv_id":"2211.05351","n_code_links":0,"syntology":null},{"paper":"/paper/cherry-hypothesis-identifying-the-cherry-on","slug":"cherry-hypothesis-identifying-the-cherry-on","title":"PAD-Net: An Efficient Framework for Dynamic Networks","date":"2022-11-10","arxiv_id":"2211.05528","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-optimizing-the-communication-of-model","title":"On Optimizing the Communication of Model Parallelism","date":"2022-11-10","arxiv_id":"2211.05322","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntax-guided-domain-adaptation-for-aspect","title":"Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05457","n_code_links":0,"syntology":null},{"paper":"/paper/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","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":["jmichaelov/collateral-facilitation"],"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":"cross-lingual-transfer-learning-for-check","title":"Cross-lingual Transfer Learning for Check-worthy Claim Identification over Twitter","date":"2022-11-09","arxiv_id":"2211.05087","n_code_links":0,"syntology":null},{"paper":"/paper/mask-more-and-mask-later-efficient-pre","slug":"mask-more-and-mask-later-efficient-pre","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","date":"2022-11-09","arxiv_id":"2211.04898","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-persian-language-review","title":"Sentiment Analysis of Persian Language: Review of Algorithms, Approaches and Datasets","date":"2022-11-09","arxiv_id":"2212.06041","n_code_links":0,"syntology":null},{"paper":"/paper/soft-augmentation-for-image-classification","slug":"soft-augmentation-for-image-classification","title":"Soft Augmentation for Image Classification","date":"2022-11-09","arxiv_id":"2211.04625","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-approach-for-dementia-detection","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","date":"2022-11-08","arxiv_id":"2211.04368","n_code_links":0,"syntology":null},{"paper":"/paper/active-example-selection-for-in-context","slug":"active-example-selection-for-in-context","title":"Active Example Selection for In-Context Learning","date":"2022-11-08","arxiv_id":"2211.04486","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":4,"n_instrument":6,"unverified":6,"pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["chicagohai/active-example-selection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"discover-explanation-improvement-automatic","title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","date":"2022-11-08","arxiv_id":"2211.04476","n_code_links":0,"syntology":null},{"paper":null,"slug":"ad-bert-using-pre-trained-contextualized","title":"AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease","date":"2022-11-07","arxiv_id":"2212.06042","n_code_links":0,"syntology":null},{"paper":"/paper/suffix-retrieval-augmented-language-modeling","slug":"suffix-retrieval-augmented-language-modeling","title":"Suffix Retrieval-Augmented Language Modeling","date":"2022-11-06","arxiv_id":"2211.03053","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-deep-cnn-state-of-the-art-for-sentiment","title":"BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets","date":"2022-11-04","arxiv_id":"2211.09733","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-long-documents-a-case-study-of","title":"BERT for Long Documents: A Case Study of Automated ICD Coding","date":"2022-11-04","arxiv_id":"2211.02519","n_code_links":0,"syntology":null},{"paper":"/paper/continuous-prompt-tuning-based-textual","slug":"continuous-prompt-tuning-based-textual","title":"Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing","date":"2022-11-04","arxiv_id":"2211.02483","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-language-models-via-epistemic","slug":"fine-tuning-language-models-via-epistemic","title":"Fine-Tuning Language Models via Epistemic Neural Networks","date":"2022-11-03","arxiv_id":"2211.01568","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["deepmind/neural_testbed"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"using-large-pre-trained-language-model-to","title":"Using Large Pre-Trained Language Model to Assist FDA in Premarket Medical Device","date":"2022-11-03","arxiv_id":"2212.01217","n_code_links":0,"syntology":null},{"paper":null,"slug":"bectra-transducer-based-end-to-end-asr-with","title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","date":"2022-11-02","arxiv_id":"2211.00792","n_code_links":0,"syntology":null}],"record_sha256":"7a10b1e33f7c3909ec5c647f4ff77a49172873483d9306d04c6b0ea1a80bd307","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}