{"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/60","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":60,"pages_in_order":108,"rows_per_page":100,"rows":[5901,6000],"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/59","next":"/method/weight-decay/papers/61","papers":[{"paper":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","n_code_links":0,"syntology":null},{"paper":null,"slug":"processing-long-legal-documents-with-pre","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","date":"2022-11-02","arxiv_id":"2211.00974","n_code_links":0,"syntology":null},{"paper":null,"slug":"wind-power-forecasting-considering-data","title":"Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach","date":"2022-11-02","arxiv_id":"2211.02674","n_code_links":0,"syntology":null},{"paper":"/paper/classactionprediction-a-challenging-benchmark","slug":"classactionprediction-a-challenging-benchmark","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","date":"2022-11-01","arxiv_id":"2211.00582","n_code_links":1,"syntology":null},{"paper":"/paper/interpretability-in-the-wild-a-circuit-for","slug":"interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","arxiv_id":"2211.00593","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["redwoodresearch/easy-transformer"],"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":"investigating-content-aware-neural-text-to","title":"Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features","date":"2022-11-01","arxiv_id":"2211.00342","n_code_links":0,"syntology":null},{"paper":null,"slug":"reduce-reuse-recycle-improving-training","title":"Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation","date":"2022-11-01","arxiv_id":"2211.00683","n_code_links":0,"syntology":null},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["davidhuji/capdec"],"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":["listed","official"]}}},{"paper":"/paper/efficient-document-retrieval-by-end-to-end","slug":"efficient-document-retrieval-by-end-to-end","title":"Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization","date":"2022-10-31","arxiv_id":"2210.17170","n_code_links":1,"syntology":null},{"paper":"/paper/gptq-accurate-post-training-quantization-for","slug":"gptq-accurate-post-training-quantization-for","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","date":"2022-10-31","arxiv_id":"2210.17323","n_code_links":17,"syntology":{"ran":5,"of":15,"n_ran_checked":2,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["ist-daslab/gptq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"leveraging-pre-trained-models-for-failure","title":"Leveraging Pre-trained Models for Failure Analysis Triplets Generation","date":"2022-10-31","arxiv_id":"2210.17497","n_code_links":0,"syntology":null},{"paper":"/paper/quala-minilm-a-quantized-length-adaptive","slug":"quala-minilm-a-quantized-length-adaptive","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","date":"2022-10-31","arxiv_id":"2210.17114","n_code_links":2,"syntology":null},{"paper":null,"slug":"sdcl-self-distillation-contrastive-learning","title":"SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking","date":"2022-10-31","arxiv_id":"2210.17168","n_code_links":0,"syntology":null},{"paper":"/paper/ssd-lm-semi-autoregressive-simplex-based","slug":"ssd-lm-semi-autoregressive-simplex-based","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","date":"2022-10-31","arxiv_id":"2210.17432","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-zero-shot-and-few-shot-table-question","title":"Towards Zero-Shot and Few-Shot Table Question Answering using GPT-3","date":"2022-10-31","arxiv_id":"2210.17284","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-decompose-hypothetical-question","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","date":"2022-10-30","arxiv_id":"2210.16865","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-tuning-makes-a-good","slug":"parameter-efficient-tuning-makes-a-good","title":"Parameter-Efficient Tuning Makes a Good Classification Head","date":"2022-10-30","arxiv_id":"2210.16771","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-meets-ctc-new-formulation-of-end-to-end","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2022-10-29","arxiv_id":"2210.16663","n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-post-training","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","date":"2022-10-29","arxiv_id":"2210.16621","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-prompt-learning-with-pre-trained","slug":"exploiting-prompt-learning-with-pre-trained","title":"Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection","date":"2022-10-29","arxiv_id":"2210.16539","n_code_links":1,"syntology":null},{"paper":"/paper/bebert-efficient-and-robust-binary-ensemble","slug":"bebert-efficient-and-robust-binary-ensemble","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","date":"2022-10-28","arxiv_id":"2210.15976","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-engineering-vs-bert-on-twitter-data","title":"Feature Engineering vs BERT on Twitter Data","date":"2022-10-28","arxiv_id":"2210.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-use-of-modality-specific-large-scale","title":"On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis","date":"2022-10-28","arxiv_id":"2210.15937","n_code_links":0,"syntology":null},{"paper":"/paper/probing-for-targeted-syntactic-knowledge","slug":"probing-for-targeted-syntactic-knowledge","title":"Probing for targeted syntactic knowledge through grammatical error detection","date":"2022-10-28","arxiv_id":"2210.16228","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-flow-vae-a-weakly-supervised-model-for-1","title":"BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classification","date":"2022-10-27","arxiv_id":"2210.15225","n_code_links":0,"syntology":null},{"paper":"/paper/coco-dr-combating-distribution-shifts-in-zero","slug":"coco-dr-combating-distribution-shifts-in-zero","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","date":"2022-10-27","arxiv_id":"2210.15212","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["openmatch/coco-dr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/cost-eff-collaborative-optimization-of","slug":"cost-eff-collaborative-optimization-of","title":"COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models","date":"2022-10-27","arxiv_id":"2210.15523","n_code_links":1,"syntology":null},{"paper":"/paper/fast-distilbert-on-cpus","slug":"fast-distilbert-on-cpus","title":"Fast DistilBERT on CPUs","date":"2022-10-27","arxiv_id":"2211.07715","n_code_links":1,"syntology":null},{"paper":"/paper/fctalker-fine-and-coarse-grained-context","slug":"fctalker-fine-and-coarse-grained-context","title":"FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis","date":"2022-10-27","arxiv_id":"2210.15360","n_code_links":1,"syntology":null},{"paper":"/paper/masked-vision-language-transformer-in-fashion","slug":"masked-vision-language-transformer-in-fashion","title":"Masked Vision-Language Transformer in Fashion","date":"2022-10-27","arxiv_id":"2210.15110","n_code_links":1,"syntology":null},{"paper":null,"slug":"trscore-a-novel-gpt-based-readability-scorer","title":"TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection","date":"2022-10-27","arxiv_id":"2210.15104","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-boundary-aware-language-model","slug":"unsupervised-boundary-aware-language-model","title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","date":"2022-10-27","arxiv_id":"2210.15231","n_code_links":2,"syntology":null},{"paper":"/paper/automatic-extraction-of-materials-and","slug":"automatic-extraction-of-materials-and","title":"Automatic extraction of materials and properties from superconductors scientific literature","date":"2022-10-26","arxiv_id":"2210.15600","n_code_links":2,"syntology":null},{"paper":null,"slug":"beyond-english-centric-bitexts-for-better","title":"Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning","date":"2022-10-26","arxiv_id":"2210.14867","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-link-bridging-inductive-link-predictions","title":"Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts","date":"2022-10-26","arxiv_id":"2210.14463","n_code_links":0,"syntology":null},{"paper":null,"slug":"don-t-prompt-search-mining-based-zero-shot","title":"Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models","date":"2022-10-26","arxiv_id":"2210.14803","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-robustness-of-prefix-tuning-in","title":"Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis","date":"2022-10-26","arxiv_id":"2211.05584","n_code_links":0,"syntology":null},{"paper":"/paper/how-long-is-enough-exploring-the-optimal","slug":"how-long-is-enough-exploring-the-optimal","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","date":"2022-10-25","arxiv_id":"2211.07713","n_code_links":1,"syntology":null},{"paper":null,"slug":"ielm-an-open-information-extraction-benchmark","title":"IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models","date":"2022-10-25","arxiv_id":"2210.14128","n_code_links":0,"syntology":null},{"paper":null,"slug":"xricl-cross-lingual-retrieval-augmented-in","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","date":"2022-10-25","arxiv_id":"2210.13693","n_code_links":0,"syntology":null},{"paper":"/paper/aacher-assorted-actor-critic-deep","slug":"aacher-assorted-actor-critic-deep","title":"AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay","date":"2022-10-24","arxiv_id":"2210.12892","n_code_links":1,"syntology":null},{"paper":"/paper/abductive-action-inference","slug":"abductive-action-inference","title":"Inferring Past Human Actions in Homes with Abductive Reasoning","date":"2022-10-24","arxiv_id":"2210.13984","n_code_links":1,"syntology":null},{"paper":null,"slug":"effective-pre-training-objectives-for","title":"Effective Pre-Training Objectives for Transformer-based Autoencoders","date":"2022-10-24","arxiv_id":"2210.13536","n_code_links":0,"syntology":null},{"paper":"/paper/emergent-world-representations-exploring-a","slug":"emergent-world-representations-exploring-a","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","date":"2022-10-24","arxiv_id":"2210.13382","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["likenneth/othello_world"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"entity-level-sentiment-analysis-in-contact","title":"Entity-level Sentiment Analysis in Contact Center Telephone Conversations","date":"2022-10-24","arxiv_id":"2210.13401","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-translationese-why-are-neural","title":"Explaining Translationese: why are Neural Classifiers Better and what do they Learn?","date":"2022-10-24","arxiv_id":"2210.13391","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-euphemism-detection-in-few-shot-and","slug":"exploring-euphemism-detection-in-few-shot-and","title":"Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings","date":"2022-10-24","arxiv_id":"2210.12926","n_code_links":1,"syntology":null},{"paper":"/paper/perfectly-secure-steganography-using-minimum","slug":"perfectly-secure-steganography-using-minimum","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","date":"2022-10-24","arxiv_id":"2210.14889","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["schroederdewitt/perfectly-secure-steganography"],"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":"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":"a-bert-based-deep-learning-approach-for","title":"A BERT-based Deep Learning Approach for Reputation Analysis in Social Media","date":"2022-10-23","arxiv_id":"2211.01954","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-essay-scoring-using-transformers","title":"Data Augmentation for Automated Essay Scoring using Transformer Models","date":"2022-10-23","arxiv_id":"2210.12809","n_code_links":0,"syntology":null},{"paper":null,"slug":"discriminative-language-model-as-semantic","title":"Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification","date":"2022-10-23","arxiv_id":"2210.12763","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-for-multiple","slug":"leveraging-large-language-models-for-multiple","title":"Leveraging Large Language Models for Multiple Choice Question Answering","date":"2022-10-22","arxiv_id":"2210.12353","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["byu-pccl/leveraging-llms-for-mcqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"meta-learning-pathologies-from-radiology","title":"Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks","date":"2022-10-22","arxiv_id":"2210.13979","n_code_links":0,"syntology":null},{"paper":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/amos-an-adam-style-optimizer-with-adaptive","slug":"amos-an-adam-style-optimizer-with-adaptive","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","date":"2022-10-21","arxiv_id":"2210.11693","n_code_links":1,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["google-research/jestimator"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffuser-efficient-transformers-with-multi","slug":"diffuser-efficient-transformers-with-multi","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","date":"2022-10-21","arxiv_id":"2210.11794","n_code_links":1,"syntology":null},{"paper":"/paper/discovering-differences-in-the-representation","slug":"discovering-differences-in-the-representation","title":"Discovering Differences in the Representation of People using Contextualized Semantic Axes","date":"2022-10-21","arxiv_id":"2210.12170","n_code_links":1,"syntology":null},{"paper":null,"slug":"littlebird-efficient-faster-longer","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","date":"2022-10-21","arxiv_id":"2210.11870","n_code_links":0,"syntology":null},{"paper":"/paper/probing-with-noise-unpicking-the-warp-and","slug":"probing-with-noise-unpicking-the-warp-and","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","date":"2022-10-21","arxiv_id":"2210.12206","n_code_links":1,"syntology":null},{"paper":null,"slug":"spabert-a-pretrained-language-model-from","title":"SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation","date":"2022-10-21","arxiv_id":"2210.12213","n_code_links":0,"syntology":null},{"paper":null,"slug":"wikiwhy-answering-and-explaining-cause-and","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","date":"2022-10-21","arxiv_id":"2210.12152","n_code_links":0,"syntology":null},{"paper":null,"slug":"3dall-e-integrating-text-to-image-ai-in-3d","title":"3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows","date":"2022-10-20","arxiv_id":"2210.11603","n_code_links":0,"syntology":null},{"paper":"/paper/composing-ensembles-of-pre-trained-models-via","slug":"composing-ensembles-of-pre-trained-models-via","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","date":"2022-10-20","arxiv_id":"2210.11522","n_code_links":0,"syntology":null},{"paper":"/paper/general-image-descriptors-for-open-world","slug":"general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","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":{"repos":["ivanaer/g-universal-clip"],"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":"/paper/a-unified-neural-network-model-for-1","slug":"a-unified-neural-network-model-for-1","title":"A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss","date":"2022-10-19","arxiv_id":"2210.10305","n_code_links":1,"syntology":null},{"paper":"/paper/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","n_code_links":4,"syntology":null},{"paper":"/paper/language-model-decomposition-quantifying-the","slug":"language-model-decomposition-quantifying-the","title":"Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models","date":"2022-10-19","arxiv_id":"2210.10289","n_code_links":1,"syntology":null},{"paper":"/paper/tempo-accelerating-transformer-based-model","slug":"tempo-accelerating-transformer-based-model","title":"Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction","date":"2022-10-19","arxiv_id":"2210.10246","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["uoft-ecosystem/tempo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"towards-a-neural-architecture-of-language","title":"Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing","date":"2022-10-19","arxiv_id":"2210.10543","n_code_links":0,"syntology":null},{"paper":"/paper/elastic-numerical-reasoning-with-adaptive","slug":"elastic-numerical-reasoning-with-adaptive","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","date":"2022-10-18","arxiv_id":"2210.10105","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 1 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":["neurasearch/neurips-2022-submission-3358"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"systematicity-in-gpt-3-s-interpretation-of","title":"Systematicity in GPT-3's Interpretation of Novel English Noun Compounds","date":"2022-10-18","arxiv_id":"2210.09492","n_code_links":0,"syntology":null},{"paper":null,"slug":"team-flow-at-drc2022-pipeline-system-for","title":"Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue","date":"2022-10-18","arxiv_id":"2210.09518","n_code_links":0,"syntology":null},{"paper":null,"slug":"tiny-attention-adapter-contexts-are-more","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","date":"2022-10-18","arxiv_id":"2211.01979","n_code_links":0,"syntology":null},{"paper":"/paper/a-generative-user-simulator-with-gpt-based","slug":"a-generative-user-simulator-with-gpt-based","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","date":"2022-10-17","arxiv_id":"2210.08692","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thu-spmi/gus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-bert-do-it-controller-area-network","title":"CAN-BERT do it? Controller Area Network Intrusion Detection System based on BERT Language Model","date":"2022-10-17","arxiv_id":"2210.09439","n_code_links":0,"syntology":null},{"paper":"/paper/idna-abf-multi-scale-deep-biological-language","slug":"idna-abf-multi-scale-deep-biological-language","title":"iDNA-ABF: multi-scale deep biological language learning model for the interpretable prediction of DNA methylations","date":"2022-10-17","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-granularity-argument-mining-in-legal","title":"Multi-granularity Argument Mining in Legal Texts","date":"2022-10-17","arxiv_id":"2210.09472","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-gpt-3-to-be-reliable","slug":"prompting-gpt-3-to-be-reliable","title":"Prompting GPT-3 To Be Reliable","date":"2022-10-17","arxiv_id":"2210.09150","n_code_links":1,"syntology":null},{"paper":"/paper/using-bottleneck-adapters-to-identify-cancer","slug":"using-bottleneck-adapters-to-identify-cancer","title":"Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints","date":"2022-10-17","arxiv_id":"2210.09440","n_code_links":1,"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":null,"slug":"acoustic-aware-non-autoregressive-spell","title":"Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding","date":"2022-10-16","arxiv_id":"2210.08665","n_code_links":0,"syntology":null},{"paper":null,"slug":"ctcbert-advancing-hidden-unit-bert-with-ctc","title":"CTCBERT: Advancing Hidden-unit BERT with CTC Objectives","date":"2022-10-16","arxiv_id":"2210.08603","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-semantic-matching-through","title":"Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion","date":"2022-10-16","arxiv_id":"2210.08471","n_code_links":0,"syntology":null},{"paper":"/paper/normsage-multi-lingual-multi-cultural-norm","slug":"normsage-multi-lingual-multi-cultural-norm","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","date":"2022-10-16","arxiv_id":"2210.08604","n_code_links":1,"syntology":null},{"paper":null,"slug":"aralegal-bert-a-pretrained-language-model-for","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","date":"2022-10-15","arxiv_id":"2210.08284","n_code_links":0,"syntology":null},{"paper":"/paper/dylora-parameter-efficient-tuning-of-pre","slug":"dylora-parameter-efficient-tuning-of-pre","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","date":"2022-10-14","arxiv_id":"2210.07558","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/kd-nlp"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/extracting-cultural-commonsense-knowledge-at","slug":"extracting-cultural-commonsense-knowledge-at","title":"Extracting Cultural Commonsense Knowledge at Scale","date":"2022-10-14","arxiv_id":"2210.07763","n_code_links":2,"syntology":null},{"paper":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","n_code_links":1,"syntology":null},{"paper":"/paper/kernel-whitening-overcome-dataset-bias-with","slug":"kernel-whitening-overcome-dataset-bias-with","title":"Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding","date":"2022-10-14","arxiv_id":"2210.07547","n_code_links":2,"syntology":null},{"paper":"/paper/testaug-a-framework-for-augmenting-capability-1","slug":"testaug-a-framework-for-augmenting-capability-1","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","date":"2022-10-14","arxiv_id":"2210.08097","n_code_links":1,"syntology":null},{"paper":"/paper/constructing-natural-language-explanations","slug":"constructing-natural-language-explanations","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","date":"2022-10-13","arxiv_id":"2210.07222","n_code_links":1,"syntology":null},{"paper":null,"slug":"explanations-from-large-language-models-make","title":"Explanations from Large Language Models Make Small Reasoners Better","date":"2022-10-13","arxiv_id":"2210.06726","n_code_links":0,"syntology":null},{"paper":null,"slug":"jointly-reinforced-user-simulator-and-task-1","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","date":"2022-10-13","arxiv_id":"2210.06706","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-of-code-are-few-shot","slug":"language-models-of-code-are-few-shot","title":"Language Models of Code are Few-Shot Commonsense Learners","date":"2022-10-13","arxiv_id":"2210.07128","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["madaan/cocogen"],"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/large-language-models-are-few-1-shot-table","slug":"large-language-models-are-few-1-shot-table","title":"Large Language Models are few(1)-shot Table Reasoners","date":"2022-10-13","arxiv_id":"2210.06710","n_code_links":1,"syntology":null},{"paper":"/paper/overlooked-video-classification-in-weakly","slug":"overlooked-video-classification-in-weakly","title":"Overlooked Video Classification in Weakly Supervised Video Anomaly Detection","date":"2022-10-13","arxiv_id":"2210.06688","n_code_links":1,"syntology":null},{"paper":null,"slug":"squat-sharpness-and-quantization-aware","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","date":"2022-10-13","arxiv_id":"2210.07171","n_code_links":0,"syntology":null},{"paper":null,"slug":"tone-prediction-and-orthographic-conversion","title":"Tone prediction and orthographic conversion for Basaa","date":"2022-10-13","arxiv_id":"2210.06986","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-sample-efficient-nlp-models-more-robust","title":"Are Sample-Efficient NLP Models More Robust?","date":"2022-10-12","arxiv_id":"2210.06456","n_code_links":0,"syntology":null}],"record_sha256":"856509d9383699db96eecaed8197f09218ba819a54e27f3e0e924cb1ed88525c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}