{"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/34","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":34,"pages_in_order":71,"rows_per_page":100,"rows":[3301,3400],"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/33","next":"/method/linear-warmup-with-linear-decay/papers/35","papers":[{"paper":null,"slug":"air-jpmc-smm4h-22-classifying-self-reported","title":"AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models","date":"2022-09-22","arxiv_id":"2209.10763","n_code_links":0,"syntology":null},{"paper":"/paper/bias-at-a-second-glance-a-deep-dive-into-bias","slug":"bias-at-a-second-glance-a-deep-dive-into-bias","title":"Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling","date":"2022-09-21","arxiv_id":"2209.10335","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["epfl-ml4ed/bias-at-a-second-glance"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/cae-mechanism-to-diminish-the-class","slug":"cae-mechanism-to-diminish-the-class","title":"CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task","date":"2022-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"representing-affect-information-in-word","title":"Representing Affect Information in Word Embeddings","date":"2022-09-21","arxiv_id":"2209.10583","n_code_links":0,"syntology":null},{"paper":null,"slug":"subject-verb-agreement-error-patterns-in","title":"Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT","date":"2022-09-21","arxiv_id":"2209.10538","n_code_links":0,"syntology":null},{"paper":null,"slug":"integer-fine-tuning-of-transformer-based","title":"Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation","date":"2022-09-20","arxiv_id":"2209.09815","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-to-many-semantic-communication-systems","title":"One-to-Many Semantic Communication Systems: Design, Implementation, Performance Evaluation","date":"2022-09-20","arxiv_id":"2209.09425","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-early-exit-in-dnns-with-multiple","slug":"unsupervised-early-exit-in-dnns-with-multiple","title":"Unsupervised Early Exit in DNNs with Multiple Exits","date":"2022-09-20","arxiv_id":"2209.09480","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-generated-scientific-papers-using","slug":"detecting-generated-scientific-papers-using","title":"Detecting Generated Scientific Papers using an Ensemble of Transformer Models","date":"2022-09-17","arxiv_id":"2209.08283","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-answer-semantic-queries-over-code","slug":"learning-to-answer-semantic-queries-over-code","title":"CodeQueries: A Dataset of Semantic Queries over Code","date":"2022-09-17","arxiv_id":"2209.08372","n_code_links":1,"syntology":null},{"paper":null,"slug":"changing-the-representation-examining-1","title":"Changing the Representation: Examining Language Representation for Neural Sign Language Production","date":"2022-09-16","arxiv_id":"2210.06312","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-reading-fast-and-slow-when-do-models","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","date":"2022-09-15","arxiv_id":"2209.07430","n_code_links":0,"syntology":null},{"paper":null,"slug":"uchecker-masked-pretrained-language-models-as","title":"uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers","date":"2022-09-15","arxiv_id":"2209.07068","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-fidelity-assessment-for-strategy","title":"Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processing","date":"2022-09-14","arxiv_id":"2209.06727","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-ensemble-approaches-for-hate","title":"BERT-based Ensemble Approaches for Hate Speech Detection","date":"2022-09-14","arxiv_id":"2209.06505","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-for-information-retrieval-are","title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?","date":"2022-09-14","arxiv_id":"2209.06583","n_code_links":0,"syntology":null},{"paper":null,"slug":"cnn-trans-enc-a-cnn-enhanced-transformer","title":"CNN-Trans-Enc: A CNN-Enhanced Transformer-Encoder On Top Of Static BERT representations for Document Classification","date":"2022-09-13","arxiv_id":"2209.06344","n_code_links":0,"syntology":null},{"paper":null,"slug":"robin-a-novel-online-suicidal-text-corpus-of-1","title":"Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale","date":"2022-09-13","arxiv_id":"2209.05707","n_code_links":0,"syntology":null},{"paper":null,"slug":"skin-skimming-intensive-long-text","title":"SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus","date":"2022-09-13","arxiv_id":"2209.05741","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-of-hazard-event-via-language","title":"A new hazard event classification model via deep learning and multifractal","date":"2022-09-12","arxiv_id":"2209.05263","n_code_links":0,"syntology":null},{"paper":null,"slug":"deck-behavioral-tests-to-improve-1","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","date":"2022-09-12","arxiv_id":"2209.05286","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-for-understanding-of-english-verb","title":"Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models","date":"2022-09-11","arxiv_id":"2209.04811","n_code_links":0,"syntology":null},{"paper":null,"slug":"yes-dlgm-a-novel-hierarchical-model-for","title":"Yes, DLGM! A novel hierarchical model for hazard classification","date":"2022-09-10","arxiv_id":"2209.04576","n_code_links":0,"syntology":null},{"paper":"/paper/echocotr-estimation-of-the-left-ventricular","slug":"echocotr-estimation-of-the-left-ventricular","title":"EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography","date":"2022-09-09","arxiv_id":"2209.04242","n_code_links":1,"syntology":null},{"paper":null,"slug":"trigger-warnings-bootstrapping-a-violence","title":"Trigger Warnings: Bootstrapping a Violence Detector for FanFiction","date":"2022-09-09","arxiv_id":"2209.04409","n_code_links":0,"syntology":null},{"paper":"/paper/claclab-at-socialdisner-using-medical","slug":"claclab-at-socialdisner-using-medical","title":"CLaCLab at SocialDisNER: Using Medical Gazetteers for Named-Entity Recognition of Disease Mentions in Spanish Tweets","date":"2022-09-08","arxiv_id":"2209.03528","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-classification-of-premise","title":"5q032e@SMM4H'22: Transformer-based classification of premise in tweets related to COVID-19","date":"2022-09-08","arxiv_id":"2209.03851","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-bidirectional-unsupervised","slug":"multilingual-bidirectional-unsupervised","title":"Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation","date":"2022-09-06","arxiv_id":"2209.02821","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-the-knowledge-of-bert-for-ctc","title":"Distilling the Knowledge of BERT for CTC-based ASR","date":"2022-09-05","arxiv_id":"2209.02030","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalization-in-neural-networks-a-broad","title":"Generalization in Neural Networks: A Broad Survey","date":"2022-09-04","arxiv_id":"2209.01610","n_code_links":0,"syntology":null},{"paper":null,"slug":"gres-graphical-cross-domain-recommendation","title":"GReS: Graphical Cross-domain Recommendation for Supply Chain Platform","date":"2022-09-02","arxiv_id":"2209.01031","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-semantic-understanding-with-self","title":"Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization","date":"2022-09-01","arxiv_id":"2209.00278","n_code_links":0,"syntology":null},{"paper":"/paper/isotropic-representation-can-improve-dense","slug":"isotropic-representation-can-improve-dense","title":"Isotropic Representation Can Improve Dense Retrieval","date":"2022-09-01","arxiv_id":"2209.00218","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-contrastive-co-training-for-event","title":"Distilling Multi-Scale Knowledge for Event Temporal Relation Extraction","date":"2022-09-01","arxiv_id":"2209.00568","n_code_links":0,"syntology":null},{"paper":"/paper/negation-detection-in-dutch-clinical-texts-an","slug":"negation-detection-in-dutch-clinical-texts-an","title":"Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods","date":"2022-09-01","arxiv_id":"2209.00470","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-clinical-natural","title":"Few-Shot Learning for Clinical Natural Language Processing Using Siamese Neural Networks","date":"2022-08-31","arxiv_id":"2208.14923","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-multi-granular-concept-extraction","slug":"large-scale-multi-granular-concept-extraction","title":"Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension","date":"2022-08-30","arxiv_id":"2208.14139","n_code_links":1,"syntology":null},{"paper":"/paper/no-means-no-a-non-im-proper-modeling-approach","slug":"no-means-no-a-non-im-proper-modeling-approach","title":"No means ‘No’; a non-im-proper modeling approach, with embedded speculative context","date":"2022-08-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"swiftpruner-reinforced-evolutionary-pruning","title":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","date":"2022-08-30","arxiv_id":"2209.00625","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-learnable-activation","slug":"transformers-with-learnable-activation","title":"Transformers with Learnable Activation Functions","date":"2022-08-30","arxiv_id":"2208.14111","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["ukplab/2022-raft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"multi-dimensional-racism-classification","title":"Multi-dimensional Racism Classification during COVID-19: Stigmatization, Offensiveness, Blame, and Exclusion","date":"2022-08-29","arxiv_id":"2208.13318","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-the-intent-landscape-of-real-world","title":"Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers","date":"2022-08-26","arxiv_id":"2208.12886","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-pre-training-and-prompt","slug":"task-specific-pre-training-and-prompt","title":"Task-specific Pre-training and Prompt Decomposition for Knowledge Graph Population with Language Models","date":"2022-08-26","arxiv_id":"2208.12539","n_code_links":1,"syntology":null},{"paper":"/paper/addressing-token-uniformity-in-transformers","slug":"addressing-token-uniformity-in-transformers","title":"Addressing Token Uniformity in Transformers via Singular Value Transformation","date":"2022-08-24","arxiv_id":"2208.11790","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":["hanqi-qi/tokenuni"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluate-confidence-instead-of-perplexity-for","title":"Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning","date":"2022-08-23","arxiv_id":"2208.11007","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-syntax-aware-bert-for-identifying-well","title":"A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework","date":"2022-08-21","arxiv_id":"2208.09912","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmsbert-clr-context-driven-modality-shifting","title":"CMSBERT-CLR: Context-driven Modality Shifting BERT with Contrastive Learning for linguistic, visual, acoustic Representations","date":"2022-08-21","arxiv_id":"2209.07424","n_code_links":0,"syntology":null},{"paper":"/paper/bspell-a-cnn-blended-bert-based-bengali-spell","slug":"bspell-a-cnn-blended-bert-based-bengali-spell","title":"BSpell: A CNN-Blended BERT Based Bangla Spell Checker","date":"2022-08-20","arxiv_id":"2208.09709","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-compressions-for-multiplicative","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","date":"2022-08-20","arxiv_id":"2208.09684","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-language-encoders-are-natural","title":"Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction","date":"2022-08-20","arxiv_id":"2208.09617","n_code_links":0,"syntology":null},{"paper":"/paper/representing-knowledge-by-spans-a-knowledge","slug":"representing-knowledge-by-spans-a-knowledge","title":"SPOT: Knowledge-Enhanced Language Representations for Information Extraction","date":"2022-08-20","arxiv_id":"2208.09625","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-augmented-cyclic-learning-framework-for","title":"Graph-Augmented Cyclic Learning Framework for Similarity Estimation of Medical Clinical Notes","date":"2022-08-19","arxiv_id":"2208.09437","n_code_links":0,"syntology":null},{"paper":"/paper/unicausal-unified-benchmark-and-model-for","slug":"unicausal-unified-benchmark-and-model-for","title":"UniCausal: Unified Benchmark and Repository for Causal Text Mining","date":"2022-08-19","arxiv_id":"2208.09163","n_code_links":1,"syntology":null},{"paper":"/paper/vault-augmenting-the-vision-and-language","slug":"vault-augmenting-the-vision-and-language","title":"VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media","date":"2022-08-18","arxiv_id":"2208.09021","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gchochla/vault"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emoment-an-emotion-annotated-mental-health","title":"EmoMent: An Emotion Annotated Mental Health Corpus from two South Asian Countries","date":"2022-08-17","arxiv_id":"2208.08486","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-encoder-for-social-science","slug":"transformer-encoder-for-social-science","title":"Transformer Encoder for Social Science","date":"2022-08-17","arxiv_id":"2208.08005","n_code_links":1,"syntology":null},{"paper":null,"slug":"continuous-active-learning-using-pretrained","title":"Continuous Active Learning Using Pretrained Transformers","date":"2022-08-15","arxiv_id":"2208.06955","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-difficulty-study-do-machines-behave-the","title":"Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?","date":"2022-08-14","arxiv_id":"2208.14509","n_code_links":0,"syntology":null},{"paper":"/paper/adan-adaptive-nesterov-momentum-algorithm-for","slug":"adan-adaptive-nesterov-momentum-algorithm-for","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","date":"2022-08-13","arxiv_id":"2208.06677","n_code_links":9,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/adan"],"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":"interpreting-bert-based-text-similarity-via","title":"Interpreting BERT-based Text Similarity via Activation and Saliency Maps","date":"2022-08-13","arxiv_id":"2208.06612","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-your-model-sensitive-spedac-a-new","title":"Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data","date":"2022-08-12","arxiv_id":"2208.06216","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-tasks-for-user-intent-detection","slug":"pre-training-tasks-for-user-intent-detection","title":"Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search","date":"2022-08-12","arxiv_id":"2208.06150","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-model-of-anaphoric-ambiguities-using-sheaf","title":"A Model of Anaphoric Ambiguities using Sheaf Theoretic Quantum-like Contextuality and BERT","date":"2022-08-11","arxiv_id":"2208.05720","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-twitter-driven-deep-learning-mechanism-for","title":"A Twitter-Driven Deep Learning Mechanism for the Determination of Vehicle Hijacking Spots in Cities","date":"2022-08-11","arxiv_id":"2208.10280","n_code_links":0,"syntology":null},{"paper":null,"slug":"searching-for-chromate-replacements-using","title":"Searching for chromate replacements using natural language processing and machine learning algorithms","date":"2022-08-11","arxiv_id":"2208.05672","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multimodal-transformer-fusing-clinical","title":"A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction","date":"2022-08-09","arxiv_id":"2208.10240","n_code_links":0,"syntology":null},{"paper":"/paper/e2eg-end-to-end-node-classification-using","slug":"e2eg-end-to-end-node-classification-using","title":"E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes","date":"2022-08-09","arxiv_id":"2208.04609","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":4,"phrase":"5 ran (of which 0 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) · 4 unverified","official":{"repos":["tuanh23/e2eg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/emotion-detection-from-tweets-using-a-bert","slug":"emotion-detection-from-tweets-using-a-bert","title":"Emotion Detection From Tweets Using a BERT and SVM Ensemble Model","date":"2022-08-09","arxiv_id":"2208.04547","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-hate-speech-detection-with","slug":"exploring-hate-speech-detection-with","title":"Exploring Hate Speech Detection with HateXplain and BERT","date":"2022-08-09","arxiv_id":"2208.04489","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-fine-tuning-of-compressed-language","title":"Efficient Fine-Tuning of Compressed Language Models with Learners","date":"2022-08-03","arxiv_id":"2208.02070","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-covid-19-fake-news","title":"A Comparative Study on COVID-19 Fake News Detection Using Different Transformer Based Models","date":"2022-08-02","arxiv_id":"2208.01355","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-classification-of-bug-reports-based","title":"Automatic Classification of Bug Reports Based on Multiple Text Information and Reports' Intention","date":"2022-08-02","arxiv_id":"2208.01274","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-gender-bias-in-retrieval-models","title":"Debiasing Gender Bias in Information Retrieval Models","date":"2022-08-02","arxiv_id":"2208.01755","n_code_links":0,"syntology":null},{"paper":"/paper/gimlps-gate-with-inhibition-mechanism-in-mlps","slug":"gimlps-gate-with-inhibition-mechanism-in-mlps","title":"giMLPs: Gate with Inhibition Mechanism in MLPs","date":"2022-08-01","arxiv_id":"2208.00929","n_code_links":1,"syntology":null},{"paper":"/paper/aggretriever-a-simple-approach-to-aggregate","slug":"aggretriever-a-simple-approach-to-aggregate","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","date":"2022-07-31","arxiv_id":"2208.00511","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-masked-autoencoder-for-self","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","date":"2022-07-30","arxiv_id":"2208.00173","n_code_links":0,"syntology":null},{"paper":"/paper/code-comment-inconsistency-detection-with","slug":"code-comment-inconsistency-detection-with","title":"Code Comment Inconsistency Detection with BERT and Longformer","date":"2022-07-29","arxiv_id":"2207.14444","n_code_links":1,"syntology":null},{"paper":null,"slug":"curriculum-learning-for-data-efficient-vision","title":"Curriculum Learning for Data-Efficient Vision-Language Alignment","date":"2022-07-29","arxiv_id":"2207.14525","n_code_links":0,"syntology":null},{"paper":null,"slug":"sercnn-stacked-embedding-recurrent-1","title":"SERCNN: Stacked Embedding Recurrent Convolutional Neural Network in Detecting Depression on Twitter","date":"2022-07-29","arxiv_id":"2207.14535","n_code_links":0,"syntology":null},{"paper":"/paper/cram-a-compression-aware-minimizer","slug":"cram-a-compression-aware-minimizer","title":"CrAM: A Compression-Aware Minimizer","date":"2022-07-28","arxiv_id":"2207.14200","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":["ist-daslab/cram"],"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":null,"slug":"sdbert-sparsedistilbert-a-faster-and-smaller","title":"SDBERT: SparseDistilBERT, a faster and smaller BERT model","date":"2022-07-28","arxiv_id":"2208.10246","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-pretraining-for-a-less","slug":"sequence-to-sequence-pretraining-for-a-less","title":"Sequence to sequence pretraining for a less-resourced Slovenian language","date":"2022-07-28","arxiv_id":"2207.13988","n_code_links":1,"syntology":null},{"paper":"/paper/soundchoice-grapheme-to-phoneme-models-with","slug":"soundchoice-grapheme-to-phoneme-models-with","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","date":"2022-07-27","arxiv_id":"2207.13703","n_code_links":1,"syntology":null},{"paper":"/paper/bundle-mcr-towards-conversational-bundle","slug":"bundle-mcr-towards-conversational-bundle","title":"Bundle MCR: Towards Conversational Bundle Recommendation","date":"2022-07-26","arxiv_id":"2207.12628","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-for-automatic-adme-semantic","title":"Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment","date":"2022-07-25","arxiv_id":"2207.12376","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-cognitive-study-on-semantic-similarity","title":"A Cognitive Study on Semantic Similarity Analysis of Large Corpora: A Transformer-based Approach","date":"2022-07-24","arxiv_id":"2207.11716","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-reasoning-behind-classification","title":"Better Reasoning Behind Classification Predictions with BERT for Fake News Detection","date":"2022-07-23","arxiv_id":"2207.11562","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-model-compression-with-random","slug":"efficient-model-compression-with-random","title":"Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing","date":"2022-07-21","arxiv_id":"2207.10702","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-collaborative-filtering-recommender","slug":"enhancing-collaborative-filtering-recommender","title":"Enhancing Collaborative Filtering Recommender with Prompt-Based Sentiment Analysis","date":"2022-07-19","arxiv_id":"2207.12883","n_code_links":1,"syntology":null},{"paper":"/paper/pic-a-phrase-in-context-dataset-for-phrase","slug":"pic-a-phrase-in-context-dataset-for-phrase","title":"PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search","date":"2022-07-19","arxiv_id":"2207.09068","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-language-models-with-domain","slug":"pre-trained-language-models-with-domain","title":"Pre-trained language models with domain knowledge for biomedical extractive summarization","date":"2022-07-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"revealing-secrets-from-pre-trained-models","title":"Revealing Secrets From Pre-trained Models","date":"2022-07-19","arxiv_id":"2207.09539","n_code_links":0,"syntology":null},{"paper":"/paper/selection-bias-induced-spurious-correlations","slug":"selection-bias-induced-spurious-correlations","title":"Selection Bias Induced Spurious Correlations in Large Language Models","date":"2022-07-18","arxiv_id":"2207.08982","n_code_links":1,"syntology":null},{"paper":"/paper/aspect-specific-context-modeling-for-aspect","slug":"aspect-specific-context-modeling-for-aspect","title":"Aspect-specific Context Modeling for Aspect-based Sentiment Analysis","date":"2022-07-17","arxiv_id":"2207.08099","n_code_links":1,"syntology":null},{"paper":"/paper/electra-is-a-zero-shot-learner-too","slug":"electra-is-a-zero-shot-learner-too","title":"ELECTRA is a Zero-Shot Learner, Too","date":"2022-07-17","arxiv_id":"2207.08141","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":["nishiwen1214/rtd-electra"],"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":"representation-learning-of-image-schema","title":"Representation Learning of Image Schema","date":"2022-07-17","arxiv_id":"2207.08256","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-action-governor-for-uncertain","title":"Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning","date":"2022-07-17","arxiv_id":"2207.08240","n_code_links":0,"syntology":null},{"paper":null,"slug":"troll-tweet-detection-using-contextualized","title":"A Context-Sensitive Word Embedding Approach for The Detection of Troll Tweets","date":"2022-07-17","arxiv_id":"2207.08230","n_code_links":0,"syntology":null},{"paper":"/paper/poet-training-neural-networks-on-tiny-devices","slug":"poet-training-neural-networks-on-tiny-devices","title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging","date":"2022-07-15","arxiv_id":"2207.07697","n_code_links":1,"syntology":null},{"paper":"/paper/position-prediction-as-an-effective","slug":"position-prediction-as-an-effective","title":"Position Prediction as an Effective Pretraining Strategy","date":"2022-07-15","arxiv_id":"2207.07611","n_code_links":1,"syntology":null}],"record_sha256":"5879a2900d66d792184bcaa1e2ec30bd086c14d20143b5f4244d64fb7bf8a0ec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}