{"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/attention-dropout/papers/73","list_of":"/method/attention-dropout","method":"Attention Dropout","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":73,"pages_in_order":109,"rows_per_page":100,"rows":[7201,7300],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention-dropout","prev":"/method/attention-dropout/papers/72","next":"/method/attention-dropout/papers/74","papers":[{"paper":null,"slug":"exploring-the-low-resource-transfer-learning","title":"Exploring the Low-Resource Transfer-Learning with mT5 model","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":"few-shot-semantic-parsing-with-language-1","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","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":"hierarchical-transformers-are-more-efficient-1","title":"Hierarchical Transformers Are More Efficient Language Models","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":"jointly-reinforced-user-simulator-and-task","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","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":"/paper/memory-assisted-prompt-editing-to-improve-gpt","slug":"memory-assisted-prompt-editing-to-improve-gpt","title":"Memory-assisted prompt editing to improve GPT-3 after deployment","date":"2022-01-16","arxiv_id":"2201.06009","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":["madaan/memprompt"],"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":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":"natural-language-deduction-through-search","title":"Natural Language Deduction through Search over Statement Compositions","date":"2022-01-16","arxiv_id":"2201.06028","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":"penguins-dont-fly-reasoning-about-generics","title":"Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","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":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","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":"reframing-human-ai-collaboration-for-1","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","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":"/paper/unifiedskg-unifying-and-multi-tasking","slug":"unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","arxiv_id":"2201.05966","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/wanli-worker-and-ai-collaboration-for-natural","slug":"wanli-worker-and-ai-collaboration-for-natural","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","date":"2022-01-16","arxiv_id":"2201.05955","n_code_links":1,"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":"when-a-sentence-does-not-introduce-a","title":"When a sentence does not introduce a discourse entity, Transformer-based models still often refer to it","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-smaller-gpt-2-models","title":"Why Does Surprisal From Smaller GPT-2 Models Provide Better Fit to Human Reading Times?","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":"commonsenseqa-2-0-exposing-the-limits-of-ai","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","date":"2022-01-14","arxiv_id":"2201.05320","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/assemble-foundation-models-for-automatic-code","slug":"assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","date":"2022-01-13","arxiv_id":"2201.05222","n_code_links":1,"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":"computational-lens-on-cognition-study-of","title":"Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow","date":"2022-01-07","arxiv_id":"2201.02662","n_code_links":0,"syntology":null},{"paper":"/paper/flow-guided-sparse-transformer-for-video","slug":"flow-guided-sparse-transformer-for-video","title":"Flow-Guided Sparse Transformer for Video Deblurring","date":"2022-01-06","arxiv_id":"2201.01893","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["linjing7/VR-Baseline"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"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},{"paper":null,"slug":"submix-practical-private-prediction-for-large-1","title":"Submix: Practical Private Prediction for Large-Scale Language Models","date":"2022-01-04","arxiv_id":"2201.00971","n_code_links":0,"syntology":null},{"paper":"/paper/an-adversarial-benchmark-for-fake-news","slug":"an-adversarial-benchmark-for-fake-news","title":"An Adversarial Benchmark for Fake News Detection Models","date":"2022-01-03","arxiv_id":"2201.00912","n_code_links":1,"syntology":null},{"paper":null,"slug":"which-student-is-best-a-comprehensive","title":"Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models","date":"2022-01-03","arxiv_id":"2201.00558","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-sensitivity-of-deep-learning-based-text","title":"On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations","date":"2022-01-02","arxiv_id":"2201.00318","n_code_links":0,"syntology":null},{"paper":"/paper/continual-stereo-matching-of-continuous","slug":"continual-stereo-matching-of-continuous","title":"Continual Stereo Matching of Continuous Driving Scenes With Growing Architecture","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"expanding-large-pre-trained-unimodal-models","title":"Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spaceedit-learning-a-unified-editing-space-1","title":"SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-neural-network-solves-and-generates","slug":"a-neural-network-solves-and-generates","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","date":"2021-12-31","arxiv_id":"2112.15594","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idrori/mathq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clustering-vietnamese-conversations-from","slug":"clustering-vietnamese-conversations-from","title":"Clustering Vietnamese Conversations From Facebook Page To Build Training Dataset For Chatbot","date":"2021-12-31","arxiv_id":"2112.15338","n_code_links":1,"syntology":null},{"paper":"/paper/multi-dimensional-model-compression-of-vision","slug":"multi-dimensional-model-compression-of-vision","title":"Multi-Dimensional Model Compression of Vision Transformer","date":"2021-12-31","arxiv_id":"2201.00043","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-mixed-precision-quantization-search","title":"Automatic Mixed-Precision Quantization Search of BERT","date":"2021-12-30","arxiv_id":"2112.14938","n_code_links":0,"syntology":null},{"paper":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","n_code_links":2,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["codecaution/evomoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"universal-transformer-hawkes-process-with","title":"Universal Transformer Hawkes Process with Adaptive Recursive Iteration","date":"2021-12-29","arxiv_id":"2112.14479","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-university-of-texas-at-dallas-hltri-s","title":"The University of Texas at Dallas HLTRI's Participation in EPIC-QA: Searching for Entailed Questions Revealing Novel Answer Nuggets","date":"2021-12-28","arxiv_id":"2112.13946","n_code_links":0,"syntology":null},{"paper":"/paper/a-passage-to-india-pre-trained-word-1","slug":"a-passage-to-india-pre-trained-word-1","title":"\"A Passage to India\": Pre-trained Word Embeddings for Indian Languages","date":"2021-12-27","arxiv_id":"2112.13800","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-sentence-analysis-for-the","title":"Contextual Sentence Analysis for the Sentiment Prediction on Financial Data","date":"2021-12-27","arxiv_id":"2112.13790","n_code_links":0,"syntology":null},{"paper":"/paper/event-based-clinical-findings-extraction-from","slug":"event-based-clinical-findings-extraction-from","title":"Event-based clinical findings extraction from radiology reports with pre-trained language model","date":"2021-12-27","arxiv_id":"2112.13512","n_code_links":1,"syntology":null},{"paper":null,"slug":"mind-the-gap-cross-lingual-information","title":"Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement","date":"2021-12-27","arxiv_id":"2112.13510","n_code_links":0,"syntology":null},{"paper":"/paper/multi-image-visual-question-answering","slug":"multi-image-visual-question-answering","title":"Multi-Image Visual Question Answering","date":"2021-12-27","arxiv_id":"2112.13706","n_code_links":1,"syntology":null},{"paper":null,"slug":"secondary-use-of-clinical-problem-list","title":"Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment","date":"2021-12-27","arxiv_id":"2112.13756","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-roberta-s-mood-the-role-of","title":"Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment","date":"2021-12-27","arxiv_id":"2112.13795","n_code_links":0,"syntology":null},{"paper":"/paper/an-ensemble-of-pre-trained-transformer-models","slug":"an-ensemble-of-pre-trained-transformer-models","title":"An Ensemble of Pre-trained Transformer Models For Imbalanced Multiclass Malware Classification","date":"2021-12-25","arxiv_id":"2112.13236","n_code_links":1,"syntology":null},{"paper":"/paper/cabace-injecting-character-sequence","slug":"cabace-injecting-character-sequence","title":"CABACE: Injecting Character Sequence Information and Domain Knowledge for Enhanced Acronym and Long-Form Extraction","date":"2021-12-25","arxiv_id":"2112.13237","n_code_links":1,"syntology":null},{"paper":"/paper/deeper-clinical-document-understanding-using","slug":"deeper-clinical-document-understanding-using","title":"Deeper Clinical Document Understanding Using Relation Extraction","date":"2021-12-25","arxiv_id":"2112.13259","n_code_links":1,"syntology":null},{"paper":"/paper/distilling-the-knowledge-of-romanian-berts","slug":"distilling-the-knowledge-of-romanian-berts","title":"Distilling the Knowledge of Romanian BERTs Using Multiple Teachers","date":"2021-12-23","arxiv_id":"2112.12650","n_code_links":1,"syntology":null}],"record_sha256":"1ee4ccc4de766d86a4ff261dcd6ed0fd4799d9a2b0195b18e7dd3f5b4d3087c8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}