{"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/39","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":39,"pages_in_order":71,"rows_per_page":100,"rows":[3801,3900],"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/38","next":"/method/linear-warmup-with-linear-decay/papers/40","papers":[{"paper":"/paper/memory-efficient-backpropagation-through","slug":"memory-efficient-backpropagation-through","title":"Memory-Efficient Backpropagation through Large Linear Layers","date":"2022-01-31","arxiv_id":"2201.13195","n_code_links":2,"syntology":null},{"paper":null,"slug":"electra-conditional-generative-model-based","title":"Electra: Conditional Generative Model based Predicate-Aware Query Approximation","date":"2022-01-28","arxiv_id":"2201.12420","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-longformer-and-clinical-bigbird","slug":"clinical-longformer-and-clinical-bigbird","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","date":"2022-01-27","arxiv_id":"2201.11838","n_code_links":1,"syntology":null},{"paper":"/paper/going-extreme-comparative-analysis-of-hate","slug":"going-extreme-comparative-analysis-of-hate","title":"Going Extreme: Comparative Analysis of Hate Speech in Parler and Gab","date":"2022-01-27","arxiv_id":"2201.11770","n_code_links":1,"syntology":null},{"paper":"/paper/grad2task-improved-few-shot-text-1","slug":"grad2task-improved-few-shot-text-1","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","date":"2022-01-27","arxiv_id":"2201.11576","n_code_links":1,"syntology":null},{"paper":"/paper/discoscore-evaluating-text-generation-with","slug":"discoscore-evaluating-text-generation-with","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","date":"2022-01-26","arxiv_id":"2201.11176","n_code_links":1,"syntology":null},{"paper":"/paper/fincat-financial-numeral-claim-analysis-tool","slug":"fincat-financial-numeral-claim-analysis-tool","title":"FiNCAT: Financial Numeral Claim Analysis Tool","date":"2022-01-26","arxiv_id":"2202.00631","n_code_links":1,"syntology":null},{"paper":"/paper/neural-grapheme-to-phoneme-conversion-with","slug":"neural-grapheme-to-phoneme-conversion-with","title":"Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models","date":"2022-01-26","arxiv_id":"2201.10716","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-3d-semantic-representation","title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation","date":"2022-01-26","arxiv_id":"2201.10788","n_code_links":0,"syntology":null},{"paper":"/paper/bertha-video-captioning-evaluation-via","slug":"bertha-video-captioning-evaluation-via","title":"BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment","date":"2022-01-25","arxiv_id":"2201.10243","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-end-to-end","title":"Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models","date":"2022-01-25","arxiv_id":"2201.10103","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-based-modeling-of-mental-disorders-on","title":"Emotion-based Modeling of Mental Disorders on Social Media","date":"2022-01-24","arxiv_id":"2201.09451","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyphone-disambiguation-and-accent","title":"Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-end","date":"2022-01-24","arxiv_id":"2201.09427","n_code_links":0,"syntology":null},{"paper":"/paper/unified-multimodal-punctuation-restoration","slug":"unified-multimodal-punctuation-restoration","title":"Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus","date":"2022-01-24","arxiv_id":"2202.00468","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-and-diverse-arabic-corpus-for","title":"A Large and Diverse Arabic Corpus for Language Modeling","date":"2022-01-23","arxiv_id":"2201.09227","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-application-of-pseudo-log-likelihoods-to","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","date":"2022-01-23","arxiv_id":"2201.09377","n_code_links":0,"syntology":null},{"paper":"/paper/black-box-prompt-learning-for-pre-trained","slug":"black-box-prompt-learning-for-pre-trained","title":"Black-box Prompt Learning for Pre-trained Language Models","date":"2022-01-21","arxiv_id":"2201.08531","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["shizhediao/black-box-prompt-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dual-contrastive-learning-text-classification","slug":"dual-contrastive-learning-text-classification","title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","date":"2022-01-21","arxiv_id":"2201.08702","n_code_links":2,"syntology":null},{"paper":null,"slug":"less-is-less-when-are-snippets-insufficient","title":"Less is Less: When Are Snippets Insufficient for Human vs Machine Relevance Estimation?","date":"2022-01-21","arxiv_id":"2201.08721","n_code_links":0,"syntology":null},{"paper":"/paper/cheating-automatic-short-answer-grading-on","slug":"cheating-automatic-short-answer-grading-on","title":"Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs","date":"2022-01-20","arxiv_id":"2201.08318","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-predicting-yelp-scores","title":"Sentiment Analysis: Predicting Yelp Scores","date":"2022-01-20","arxiv_id":"2201.07999","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-approaches-for-building","slug":"transfer-learning-approaches-for-building","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","date":"2022-01-20","arxiv_id":"2201.08471","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hltcoe/colbert-x"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/near-optimal-sparse-allreduce-for-distributed","slug":"near-optimal-sparse-allreduce-for-distributed","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","date":"2022-01-19","arxiv_id":"2201.07598","n_code_links":1,"syntology":null},{"paper":null,"slug":"tourbert-a-pretrained-language-model-for-the","title":"TourBERT: A pretrained language model for the tourism industry","date":"2022-01-19","arxiv_id":"2201.07449","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-neural-network-approaches-for","title":"Hierarchical Neural Network Approaches for Long Document Classification","date":"2022-01-18","arxiv_id":"2201.06774","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-vs-albert-explained","title":"BERT vs ALBERT explained","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/mulve-a-multi-language-vocabulary-evaluation","slug":"mulve-a-multi-language-vocabulary-evaluation","title":"MuLVE, A Multi-Language Vocabulary Evaluation Data Set","date":"2022-01-17","arxiv_id":"2201.06286","n_code_links":0,"syntology":null},{"paper":null,"slug":"unintended-bias-in-language-model","title":"Unintended Bias in Language Model-driven Conversational Recommendation","date":"2022-01-17","arxiv_id":"2201.06224","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-balanced-data-approach-for-evaluating-cross","title":"A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-granularity-opinion-summarization","title":"A Multi-Granularity Opinion Summarization Method","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-the-attention-abnormality-in","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploitation-of-heterogeneous-graph-neural","title":"An Exploitation of Heterogeneous Graph Neural Network for Extractive Long Document Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-softtriple-loss-for-supervised-1","title":"Applying SoftTriple Loss for Supervised Language Model Fine Tuning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"autoattention-automatic-attention-head","title":"AutoAttention: Automatic Attention Head Selection Through Differentiable Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bridge-the-gap-between-cv-and-nlp-a-gradient-1","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-conduct-logical-reasoning-on-the","title":"Can BERT Conduct Logical Reasoning? On the Difficulty of Learning to Reason from Data","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-customize-a-unique","title":"Context-Aware Prompt: Customize A Unique Prompt For Each Input","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deck-behavioral-tests-to-improve","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-and-conquer-text-semantic-matching","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-berts-learn-to-use-browser-user-interface","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eici-a-new-method-of-dynamic-embedding","title":"EiCi: A New Method of Dynamic Embedding Incorporating Contextual Information in Chinese NER","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-detection-via-derangement-reading","title":"Event Detection via Derangement Reading Comprehension","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-adversarial-attacks-on-text-1","title":"Experiments with adversarial attacks on text genres","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feasibility-of-bert-embeddings-for-domain","title":"Feasibility of BERT Embeddings For Domain-Specific Knowledge Mining","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fednlp-benchmarking-federated-learning","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"global-entity-disambiguation-with-bert","title":"Global Entity Disambiguation with BERT","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-the-source-of-vulnerability-in","title":"Identifying the Source of Vulnerability in Fragile Interpretations: A Case Study in Neural Text Classification","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impli-investigatng-nli-models-performance-on","title":"IMPLI: Investigatng NLI Models' Performance on Figurative Language","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-contextual-representation-with","title":"Improving Contextual Representation with Gloss Regularized Pre-training","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-and-explaining-feature-and","title":"Investigating and Explaining Feature and Representation Learning in Translationese Classification","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-saliency-of-sentiment","title":"Investigating the saliency of sentiment expressions in aspect-based sentiment analysis","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-for-code-switch-detection-of","title":"Language Models for Code-switch Detection of te reo Māori and English in a Low-resource Setting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with-1","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-word-context-biases-in-lexical","title":"Measuring Word-Context Biases in Lexical Semantic Datasets","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"minimally-supervised-relation-induction-from","title":"Minimally-Supervised Relation Induction from Pre-trained Language Model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-multi-granularity-hierarchical","title":"Modeling Multi-Granularity Hierarchical Features for Relation Extraction","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-stage-pre-training-for-math","title":"Multi-Stage Pre-Training for Math-Understanding: $\\mu^2$(AL)BERT","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pcee-bert-accelerating-bert-inference-via","title":"PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-the-linguistic-capacity-of-pre","title":"Probing The Linguistic Capacity of Pre-Trained Vision-Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"progressive-class-semantic-matching-for-semi","title":"Progressive Class Semantic Matching for Semi-supervised Text Classification","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational-1","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-additive-compositionality-and-or-1","title":"Revisiting Additive Compositionality: AND, OR, and NOT Operations with Word Embeddings","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robin-a-novel-online-suicidal-text-corpus-of","title":"Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"roof-bert-divide-understanding-labour-and-1","title":"Roof-BERT: Divide Understanding Labour and Join in Work","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semattack-natural-textual-attacks-via","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seq-gan-bert-sequence-generative-adversarial","title":"Seq-GAN-BERT：Sequence Generative Adversarial Learning for Low-resource Name Entity Recognition","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-local-attentions-remain-competitive-1","title":"Simple Local Attentions Remain Competitive for Long-Context Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tacl-improving-bert-pre-training-with-token-1","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tapping-bert-for-preposition-sense-1","title":"Tapping BERT for Preposition Sense Disambiguation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"template-temprel-classification-model-trained","title":"TEMPLATE: TempRel Classification Model Trained with Embedded Temporal Relation Knowledge","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"that-is-a-good-looking-car-visual-aspect","title":"That is a good looking car !: Visual Aspect based Sentiment Controlled Personalized Response Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-knowledge-distillation-for-compressing","title":"Tree Knowledge Distillation for Compressing Transformer-Based Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"uncovering-surprising-event-boundaries-in","title":"Uncovering Surprising Event Boundaries in Narratives","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understand-before-answer-improve-temporal","title":"Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vee-bert-accelerating-bert-inference-for","title":"VEE-BERT: Accelerating BERT Inference for Named Entity Recognition via Vote Early Exiting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/what-do-tokens-know-about-their-characters","slug":"what-do-tokens-know-about-their-characters","title":"What do tokens know about their characters and how do they know it?","date":"2022-01-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"what-role-does-bert-play-in-the-neural","title":"What Role Does BERT Play in the Neural Machine Translation Encoder?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-correction-of-syntactic-dependency","title":"Automatic Correction of Syntactic Dependency Annotation Differences","date":"2022-01-15","arxiv_id":"2201.05891","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-lexical-simplification-for-turkish","title":"Automatic Lexical Simplification for Turkish","date":"2022-01-15","arxiv_id":"2201.05878","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-for-food-review-and","title":"Machine Learning for Food Review and Recommendation","date":"2022-01-15","arxiv_id":"2201.10978","n_code_links":0,"syntology":null},{"paper":null,"slug":"polarity-and-subjectivity-detection-with","title":"Polarity and Subjectivity Detection with Multitask Learning and BERT Embedding","date":"2022-01-14","arxiv_id":"2201.05363","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-graph-augmented-network-towards","slug":"knowledge-graph-augmented-network-towards","title":"Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis","date":"2022-01-13","arxiv_id":"2201.04831","n_code_links":1,"syntology":null},{"paper":"/paper/lp-bert-multi-task-pre-training-knowledge","slug":"lp-bert-multi-task-pre-training-knowledge","title":"Multi-task Pre-training Language Model for Semantic Network Completion","date":"2022-01-13","arxiv_id":"2201.04843","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-automated-error-analysis-learning-to","title":"Towards Automated Error Analysis: Learning to Characterize Errors","date":"2022-01-13","arxiv_id":"2201.05017","n_code_links":0,"syntology":null},{"paper":"/paper/diagnosing-bert-with-retrieval-heuristics","slug":"diagnosing-bert-with-retrieval-heuristics","title":"Diagnosing BERT with Retrieval Heuristics","date":"2022-01-12","arxiv_id":"2201.04458","n_code_links":1,"syntology":null},{"paper":"/paper/generative-adversarial-network-for-text-to","slug":"generative-adversarial-network-for-text-to","title":"Generative Adversarial Network for Text-to-Face Synthesis and Manipulation with Pretrained BERT Model","date":"2022-01-12","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/promptbert-improving-bert-sentence-embeddings-1","slug":"promptbert-improving-bert-sentence-embeddings-1","title":"PromptBERT: Improving BERT Sentence Embeddings with Prompts","date":"2022-01-12","arxiv_id":"2201.04337","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":5,"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) · 4 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["kongds/prompt-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-feature-extraction-based-model-for-hate","title":"A Feature Extraction based Model for Hate Speech Identification","date":"2022-01-11","arxiv_id":"2201.04227","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-prediction-uncertainty-of-pre","title":"Explaining Predictive Uncertainty by Looking Back at Model Explanations","date":"2022-01-11","arxiv_id":"2201.03742","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-robustness-to-adversarial-word","title":"Quantifying Robustness to Adversarial Word Substitutions","date":"2022-01-11","arxiv_id":"2201.03829","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-sentiment-analysis-pre-trained-and","slug":"bert-for-sentiment-analysis-pre-trained-and","title":"BERT for Sentiment Analysis: Pre-trained and Fine-Tuned Alternatives","date":"2022-01-10","arxiv_id":"2201.03382","n_code_links":2,"syntology":null},{"paper":"/paper/black-box-tuning-for-language-model-as-a","slug":"black-box-tuning-for-language-model-as-a","title":"Black-Box Tuning for Language-Model-as-a-Service","date":"2022-01-10","arxiv_id":"2201.03514","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["txsun1997/black-box-tuning"],"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":"fully-automatic-scoring-of-handwritten","title":"Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests","date":"2022-01-10","arxiv_id":"2201.03215","n_code_links":0,"syntology":null},{"paper":"/paper/scrolls-standardized-comparison-over-long","slug":"scrolls-standardized-comparison-over-long","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","date":"2022-01-10","arxiv_id":"2201.03533","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tau-nlp/scrolls"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tiltedbert-resource-adjustable-version-of","title":"Latency Adjustable Transformer Encoder for Language Understanding","date":"2022-01-10","arxiv_id":"2201.03327","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-training-vision-language-berts-with-a","title":"Self-Training Vision Language BERTs with a Unified Conditional Model","date":"2022-01-06","arxiv_id":"2201.02010","n_code_links":0,"syntology":null},{"paper":null,"slug":"formal-analysis-of-art-proxy-learning-of","title":"Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models","date":"2022-01-05","arxiv_id":"2201.01819","n_code_links":0,"syntology":null},{"paper":"/paper/learning-audio-visual-speech-representation-1","slug":"learning-audio-visual-speech-representation-1","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","date":"2022-01-05","arxiv_id":"2201.02184","n_code_links":2,"syntology":null},{"paper":"/paper/relationship-extraction-for-knowledge-graph","slug":"relationship-extraction-for-knowledge-graph","title":"Comparison of biomedical relationship extraction methods and models for knowledge graph creation","date":"2022-01-05","arxiv_id":"2201.01647","n_code_links":0,"syntology":null}],"record_sha256":"d59e99d4237bf6d994b3578340cfe5e2fe655c6e972c4d776cdcfc71b8bba22d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}