{"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/linear-warmup-with-linear-decay/papers/27","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear 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":27,"pages_in_order":71,"rows_per_page":100,"rows":[2601,2700],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/26","next":"/method/linear-warmup-with-linear-decay/papers/28","papers":[{"paper":"/paper/can-model-fusing-help-transformers-in-long","slug":"can-model-fusing-help-transformers-in-long","title":"Can Model Fusing Help Transformers in Long Document Classification? An Empirical Study","date":"2023-07-18","arxiv_id":"2307.09532","n_code_links":1,"syntology":null},{"paper":null,"slug":"katie-a-system-for-key-attributes","title":"KATIE: A System for Key Attributes Identification in Product Knowledge Graph Construction","date":"2023-07-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-ner-for-financial-transaction","title":"Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages","date":"2023-07-16","arxiv_id":"2307.08714","n_code_links":0,"syntology":null},{"paper":null,"slug":"recognition-of-mental-adjectives-in-an","title":"Recognition of Mental Adjectives in An Efficient and Automatic Style","date":"2023-07-16","arxiv_id":"2307.11767","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-not-mask-randomly-effective-domain","title":"Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords","date":"2023-07-14","arxiv_id":"2307.07160","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bert-with-hybrid-pooling-network","title":"Improving BERT with Hybrid Pooling Network and Drop Mask","date":"2023-07-14","arxiv_id":"2307.07258","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensi-bert-towards-sensitivity-driven-fine","title":"Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT","date":"2023-07-14","arxiv_id":"2307.11764","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-spoken-dialect-identification-of","title":"Towards spoken dialect identification of Irish","date":"2023-07-14","arxiv_id":"2307.07436","n_code_links":0,"syntology":null},{"paper":null,"slug":"tvpr-text-to-video-person-retrieval-and-a-new","title":"TVPR: Text-to-Video Person Retrieval and a New Benchmark","date":"2023-07-14","arxiv_id":"2307.07184","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-networks-for-sentiment-2","title":"Convolutional Neural Networks for Sentiment Analysis on Weibo Data: A Natural Language Processing Approach","date":"2023-07-13","arxiv_id":"2307.06540","n_code_links":0,"syntology":null},{"paper":null,"slug":"securefalcon-the-next-cyber-reasoning-system","title":"SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?","date":"2023-07-13","arxiv_id":"2307.06616","n_code_links":0,"syntology":null},{"paper":"/paper/tackling-fake-news-in-bengali-unraveling-the","slug":"tackling-fake-news-in-bengali-unraveling-the","title":"Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models","date":"2023-07-13","arxiv_id":"2307.06979","n_code_links":1,"syntology":null},{"paper":"/paper/towards-populating-generalizable-engineering","slug":"towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","n_code_links":2,"syntology":null},{"paper":null,"slug":"detecting-the-presence-of-covid-19","title":"Detecting the Presence of COVID-19 Vaccination Hesitancy from South African Twitter Data Using Machine Learning","date":"2023-07-12","arxiv_id":"2307.15072","n_code_links":0,"syntology":null},{"paper":"/paper/no-train-no-gain-revisiting-efficient","slug":"no-train-no-gain-revisiting-efficient","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","date":"2023-07-12","arxiv_id":"2307.06440","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jeankaddour/notrainnogain"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"prompt-generate-train-pgt-a-framework-for-few","title":"Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering","date":"2023-07-12","arxiv_id":"2307.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"vacaspati-a-diverse-corpus-of-bangla","title":"Vacaspati: A Diverse Corpus of Bangla Literature","date":"2023-07-11","arxiv_id":"2307.05083","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-for-digital-forensic-investigation","slug":"chatgpt-for-digital-forensic-investigation","title":"ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown","date":"2023-07-10","arxiv_id":"2307.10195","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-chatgpt-a-good-personality-recognizer-a","title":"Is ChatGPT a Good Personality Recognizer? A Preliminary Study","date":"2023-07-08","arxiv_id":"2307.03952","n_code_links":0,"syntology":null},{"paper":null,"slug":"goal-conditioned-predictive-coding-as-an","title":"Goal-Conditioned Predictive Coding for Offline Reinforcement Learning","date":"2023-07-07","arxiv_id":"2307.03406","n_code_links":0,"syntology":null},{"paper":"/paper/trac-trustworthy-retrieval-augmented-chatbot","slug":"trac-trustworthy-retrieval-augmented-chatbot","title":"TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction","date":"2023-07-07","arxiv_id":"2307.04642","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-site-agnostic-multimodal-deep","title":"A Novel Site-Agnostic Multimodal Deep Learning Model to Identify Pro-Eating Disorder Content on Social Media","date":"2023-07-06","arxiv_id":"2307.06775","n_code_links":0,"syntology":null},{"paper":"/paper/can-chatgpt-s-responses-boost-traditional","slug":"can-chatgpt-s-responses-boost-traditional","title":"Can ChatGPT's Responses Boost Traditional Natural Language Processing?","date":"2023-07-06","arxiv_id":"2307.04648","n_code_links":1,"syntology":null},{"paper":"/paper/text-alignment-is-an-efficient-unified-model","slug":"text-alignment-is-an-efficient-unified-model","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","date":"2023-07-06","arxiv_id":"2307.02729","n_code_links":1,"syntology":null},{"paper":null,"slug":"uit-saviors-at-medvqa-gi-2023-improving","title":"UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering","date":"2023-07-06","arxiv_id":"2307.02783","n_code_links":0,"syntology":null},{"paper":"/paper/came-confidence-guided-adaptive-memory","slug":"came-confidence-guided-adaptive-memory","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","date":"2023-07-05","arxiv_id":"2307.02047","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"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":["yangluo7/came","huawei-noah/Pretrained-Language-Model"],"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/emoji-prediction-using-transformer-models","slug":"emoji-prediction-using-transformer-models","title":"Emoji Prediction in Tweets using BERT","date":"2023-07-05","arxiv_id":"2307.02054","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-large","title":"Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations","date":"2023-07-05","arxiv_id":"2307.03678","n_code_links":0,"syntology":null},{"paper":null,"slug":"named-entity-inclusion-in-abstractive-text-1","title":"Named Entity Inclusion in Abstractive Text Summarization","date":"2023-07-05","arxiv_id":"2307.02570","n_code_links":0,"syntology":null},{"paper":"/paper/kdstm-neural-semi-supervised-topic-modeling","slug":"kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","arxiv_id":"2307.01878","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 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) · 2 unverified","official":null}},{"paper":null,"slug":"alberti-a-multilingual-domain-specific","title":"ALBERTI, a Multilingual Domain Specific Language Model for Poetry Analysis","date":"2023-07-03","arxiv_id":"2307.01387","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-plasticity-via-pretraining","slug":"improving-language-plasticity-via-pretraining","title":"Improving Language Plasticity via Pretraining with Active Forgetting","date":"2023-07-03","arxiv_id":"2307.01163","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretability-and-transparency-driven","title":"Interpretability and Transparency-Driven Detection and Transformation of Textual Adversarial Examples (IT-DT)","date":"2023-07-03","arxiv_id":"2307.01225","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-is-language-model-from-100-few-shot","slug":"how-far-is-language-model-from-100-few-shot","title":"How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain","date":"2023-07-01","arxiv_id":"2307.00186","n_code_links":1,"syntology":null},{"paper":null,"slug":"ticket-bert-labeling-incident-management","title":"Ticket-BERT: Labeling Incident Management Tickets with Language Models","date":"2023-06-30","arxiv_id":"2307.00108","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-crime-types-using-judgment","title":"Classifying Crime Types using Judgment Documents from Social Media","date":"2023-06-29","arxiv_id":"2306.17020","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-hugging-face","title":"Harnessing the Power of Hugging Face Transformers for Predicting Mental Health Disorders in Social Networks","date":"2023-06-29","arxiv_id":"2306.16891","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-sparse-inference-software","slug":"an-efficient-sparse-inference-software","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","date":"2023-06-28","arxiv_id":"2306.16601","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-the-hype-assessing-the-performance","title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","date":"2023-06-28","arxiv_id":"2306.15887","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-site-clinical-federated-learning-using","title":"Multi-Site Clinical Federated Learning using Recursive and Attentive Models and NVFlare","date":"2023-06-28","arxiv_id":"2306.16367","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-in-bert-measuring-and-analysing-1","title":"Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task","date":"2023-06-27","arxiv_id":"2306.15298","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-cross-domain-behaviors-of-bert","title":"Investigating Cross-Domain Behaviors of BERT in Review Understanding","date":"2023-06-27","arxiv_id":"2306.15123","n_code_links":0,"syntology":null},{"paper":null,"slug":"mat-mixed-strategy-game-of-adversarial","title":"MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning","date":"2023-06-27","arxiv_id":"2306.15826","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparseoptimizer-sparsify-language-models","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","date":"2023-06-27","arxiv_id":"2306.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-power-of-user-reviews","title":"Unleashing the Power of User Reviews: Exploring Airline Choices at Catania Airport, Italy","date":"2023-06-27","arxiv_id":"2306.15541","n_code_links":0,"syntology":null},{"paper":"/paper/constraint-aware-and-ranking-distilled-token","slug":"constraint-aware-and-ranking-distilled-token","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","date":"2023-06-26","arxiv_id":"2306.14393","n_code_links":1,"syntology":null},{"paper":null,"slug":"addressing-cold-start-problem-for-end-to-end","title":"Addressing Cold Start Problem for End-to-end Automatic Speech Scoring","date":"2023-06-25","arxiv_id":"2306.14310","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-cyber-threat-detection-with","title":"Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices","date":"2023-06-25","arxiv_id":"2306.14263","n_code_links":0,"syntology":null},{"paper":null,"slug":"switch-bert-learning-to-model-multimodal","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","date":"2023-06-25","arxiv_id":"2306.14182","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-pre-trained-language-models-for","title":"Comparison of Pre-trained Language Models for Turkish Address Parsing","date":"2023-06-24","arxiv_id":"2306.13947","n_code_links":0,"syntology":null},{"paper":null,"slug":"ierl-interpretable-ensemble-representation","title":"IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations","date":"2023-06-24","arxiv_id":"2306.13865","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahasent-md-a-multi-domain-marathi","slug":"l3cube-mahasent-md-a-multi-domain-marathi","title":"L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models","date":"2023-06-24","arxiv_id":"2306.13888","n_code_links":1,"syntology":null},{"paper":"/paper/math-word-problem-solving-by-generating","slug":"math-word-problem-solving-by-generating","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","date":"2023-06-24","arxiv_id":"2306.13899","n_code_links":1,"syntology":null},{"paper":"/paper/my-boli-code-mixed-marathi-english-corpora","slug":"my-boli-code-mixed-marathi-english-corpora","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","date":"2023-06-24","arxiv_id":"2306.14030","n_code_links":1,"syntology":null},{"paper":null,"slug":"partitioning-guided-k-means-extreme-empty","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","date":"2023-06-24","arxiv_id":"2306.14031","n_code_links":0,"syntology":null},{"paper":null,"slug":"resume-information-extraction-via-post-ocr","title":"Resume Information Extraction via Post-OCR Text Processing","date":"2023-06-23","arxiv_id":"2306.13775","n_code_links":0,"syntology":null},{"paper":null,"slug":"named-entity-recognition-in-resumes","title":"Named entity recognition in resumes","date":"2023-06-22","arxiv_id":"2306.13062","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-pre-trained-language-models-on","title":"Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI","date":"2023-06-21","arxiv_id":"2306.12205","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-language-models-for-scientific","slug":"fine-tuning-language-models-for-scientific","title":"Fine-Tuning Language Models for Scientific Writing Support","date":"2023-06-19","arxiv_id":"2306.10974","n_code_links":1,"syntology":null},{"paper":"/paper/instant-soup-cheap-pruning-ensembles-in-a","slug":"instant-soup-cheap-pruning-ensembles-in-a","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","date":"2023-06-18","arxiv_id":"2306.10460","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":["vita-group/instant_soup"],"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":"investigating-masking-based-data-generation","title":"Investigating Masking-based Data Generation in Language Models","date":"2023-06-16","arxiv_id":"2307.00008","n_code_links":0,"syntology":null},{"paper":null,"slug":"revealing-the-impact-of-social-circumstances","title":"Revealing the impact of social circumstances on the selection of cancer therapy through natural language processing of social work notes","date":"2023-06-16","arxiv_id":"2306.09877","n_code_links":0,"syntology":null},{"paper":"/paper/bed-bi-encoder-based-detectors-for-out-of","slug":"bed-bi-encoder-based-detectors-for-out-of","title":"BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection","date":"2023-06-15","arxiv_id":"2306.08852","n_code_links":1,"syntology":null},{"paper":null,"slug":"distillation-strategies-for-discriminative","title":"Distillation Strategies for Discriminative Speech Recognition Rescoring","date":"2023-06-15","arxiv_id":"2306.09452","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapping-researcher-activity-based-on","title":"Mapping Researcher Activity based on Publication Data by means of Transformers","date":"2023-06-15","arxiv_id":"2306.09049","n_code_links":0,"syntology":null},{"paper":"/paper/slamb-accelerated-large-batch-training-with","slug":"slamb-accelerated-large-batch-training-with","title":"SLAMB: Accelerated Large Batch Training with Sparse Communication","date":"2023-06-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-re-weighted-gradient-descent-via","title":"Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization","date":"2023-06-15","arxiv_id":"2306.09222","n_code_links":0,"syntology":null},{"paper":"/paper/a-semantically-enhanced-dual-encoder-for","slug":"a-semantically-enhanced-dual-encoder-for","title":"A semantically enhanced dual encoder for aspect sentiment triplet extraction","date":"2023-06-14","arxiv_id":"2306.08373","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-corpus-for-biomedical-relation","title":"Building a Corpus for Biomedical Relation Extraction of Species Mentions","date":"2023-06-14","arxiv_id":"2306.08403","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-on-named-entity-recognition-in","title":"Research on Named Entity Recognition in Improved transformer with R-Drop structure","date":"2023-06-14","arxiv_id":"2306.08315","n_code_links":0,"syntology":null},{"paper":"/paper/world-to-words-grounded-open-vocabulary","slug":"world-to-words-grounded-open-vocabulary","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","date":"2023-06-14","arxiv_id":"2306.08685","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["sled-group/world-to-words"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"gemo-clap-gender-attribute-enhanced","title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","date":"2023-06-13","arxiv_id":"2306.07848","n_code_links":0,"syntology":null},{"paper":"/paper/improving-zero-shot-detection-of-low","slug":"improving-zero-shot-detection-of-low","title":"Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models","date":"2023-06-13","arxiv_id":"2306.08000","n_code_links":1,"syntology":null},{"paper":null,"slug":"monolingual-and-cross-lingual-knowledge","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","date":"2023-06-13","arxiv_id":"2306.07797","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"imbalanced-multi-label-classification-for","title":"Imbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces","date":"2023-06-12","arxiv_id":"2306.07046","n_code_links":0,"syntology":null},{"paper":"/paper/linear-classifier-an-often-forgotten-baseline","slug":"linear-classifier-an-often-forgotten-baseline","title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","date":"2023-06-12","arxiv_id":"2306.07111","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["jameslyc88/text_classification_baseline_code"],"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"]}}},{"paper":null,"slug":"multimodal-audio-textual-architecture-for-1","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","date":"2023-06-12","arxiv_id":"2306.06819","n_code_links":0,"syntology":null},{"paper":"/paper/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":null,"slug":"robertweet-a-bert-language-model-for-romanian","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","date":"2023-06-11","arxiv_id":"2306.06598","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-low-resource-ner-using-assisting","title":"Enhancing Low Resource NER Using Assisting Language And Transfer Learning","date":"2023-06-10","arxiv_id":"2306.06477","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-data-augmentation-via-chatgpt-a-case","title":"Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification","date":"2023-06-10","arxiv_id":"2306.07297","n_code_links":0,"syntology":null},{"paper":null,"slug":"cover-a-heuristic-greedy-adversarial-attack","title":"COVER: A Heuristic Greedy Adversarial Attack on Prompt-based Learning in Language Models","date":"2023-06-09","arxiv_id":"2306.05659","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-network-compression-via","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","date":"2023-06-09","arxiv_id":"2306.05785","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-bert-and-fine-tuned-roberta-to","title":"Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT","date":"2023-06-09","arxiv_id":"2306.07401","n_code_links":0,"syntology":null},{"paper":"/paper/prodigy-an-expeditiously-adaptive-parameter","slug":"prodigy-an-expeditiously-adaptive-parameter","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","date":"2023-06-09","arxiv_id":"2306.06101","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-telecom-language-through-large","title":"Understanding Telecom Language Through Large Language Models","date":"2023-06-09","arxiv_id":"2306.07933","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-hessians-with-inter-layer","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","date":"2023-06-08","arxiv_id":"2306.04879","n_code_links":0,"syntology":null},{"paper":"/paper/bias-against-93-stigmatized-groups-in-masked","slug":"bias-against-93-stigmatized-groups-in-masked","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","date":"2023-06-08","arxiv_id":"2306.05550","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["mooniem/mlms_bias_stigmas"],"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/extensive-evaluation-of-transformer-based","slug":"extensive-evaluation-of-transformer-based","title":"Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extraction","date":"2023-06-08","arxiv_id":"2306.05276","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-language-identification-to-enhance","title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","date":"2023-06-08","arxiv_id":"2306.04964","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-supernets-improving-weight-sharing","slug":"mixture-of-supernets-improving-weight-sharing","title":"Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts","date":"2023-06-08","arxiv_id":"2306.04845","n_code_links":1,"syntology":null},{"paper":null,"slug":"nowj-at-coliee-2023-multi-task-and-ensemble","title":"NOWJ at COLIEE 2023 -- Multi-Task and Ensemble Approaches in Legal Information Processing","date":"2023-06-08","arxiv_id":"2306.04903","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-analysis-of-parameter-efficient","slug":"an-empirical-analysis-of-parameter-efficient","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.04067","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-human-rights-violations-on-social","title":"Detecting Human Rights Violations on Social Media during Russia-Ukraine War","date":"2023-06-06","arxiv_id":"2306.05370","n_code_links":0,"syntology":null},{"paper":"/paper/leace-perfect-linear-concept-erasure-in","slug":"leace-perfect-linear-concept-erasure-in","title":"LEACE: Perfect linear concept erasure in closed form","date":"2023-06-06","arxiv_id":"2306.03819","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":10,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["eleutherai/concept-erasure"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/on-the-difference-of-bert-style-and-clip","slug":"on-the-difference-of-bert-style-and-clip","title":"On the Difference of BERT-style and CLIP-style Text Encoders","date":"2023-06-06","arxiv_id":"2306.03678","n_code_links":1,"syntology":null},{"paper":"/paper/comet-learning-cardinality-constrained","slug":"comet-learning-cardinality-constrained","title":"COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search","date":"2023-06-05","arxiv_id":"2306.02824","n_code_links":2,"syntology":null},{"paper":null,"slug":"on-scientific-debt-in-nlp-a-case-for-more","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","date":"2023-06-05","arxiv_id":"2306.02870","n_code_links":0,"syntology":null}],"record_sha256":"1242509aa3981053ae5c2c9f0dba62f64d365494bf1a75e14c6ee3e43e445987","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}