{"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/69","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":69,"pages_in_order":109,"rows_per_page":100,"rows":[6801,6900],"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/68","next":"/method/attention-dropout/papers/70","papers":[{"paper":null,"slug":"deep-learning-based-chinese-text-sentiment","title":"Deep learning based Chinese text sentiment mining and stock market correlation research","date":"2022-05-10","arxiv_id":"2205.04743","n_code_links":0,"syntology":null},{"paper":"/paper/problems-with-cosine-as-a-measure-of","slug":"problems-with-cosine-as-a-measure-of","title":"Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words","date":"2022-05-10","arxiv_id":"2205.05092","n_code_links":2,"syntology":null},{"paper":null,"slug":"ratatouille-a-tool-for-novel-recipe","title":"Ratatouille: A tool for Novel Recipe Generation","date":"2022-05-10","arxiv_id":"2206.08267","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-activation-recomputation-in-large","slug":"reducing-activation-recomputation-in-large","title":"Reducing Activation Recomputation in Large Transformer Models","date":"2022-05-10","arxiv_id":"2205.05198","n_code_links":4,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","n_code_links":2,"syntology":{"ran":15,"of":16,"n_ran_checked":15,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/google-research"],"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":"automated-evaluation-for-student","title":"Automated Evaluation for Student Argumentative Writing: A Survey","date":"2022-05-09","arxiv_id":"2205.04083","n_code_links":0,"syntology":null},{"paper":"/paper/long-document-re-ranking-with-modular-re","slug":"long-document-re-ranking-with-modular-re","title":"Long Document Re-ranking with Modular Re-ranker","date":"2022-05-09","arxiv_id":"2205.04275","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-segment-preserving-sampling-for-deep","title":"Multi-segment preserving sampling for deep manifold sampler","date":"2022-05-09","arxiv_id":"2205.04259","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-the-correlation-between-text","title":"Research on the correlation between text emotion mining and stock market based on deep learning","date":"2022-05-09","arxiv_id":"2205.06675","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-use-of-bert-for-automated-essay","slug":"on-the-use-of-bert-for-automated-essay","title":"On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation","date":"2022-05-08","arxiv_id":"2205.03835","n_code_links":1,"syntology":null},{"paper":"/paper/aki-bert-a-pre-trained-clinical-language","slug":"aki-bert-a-pre-trained-clinical-language","title":"AKI-BERT: a Pre-trained Clinical Language Model for Early Prediction of Acute Kidney Injury","date":"2022-05-07","arxiv_id":"2205.03695","n_code_links":1,"syntology":null},{"paper":"/paper/emotionflow-capture-the-dialogue-level","slug":"emotionflow-capture-the-dialogue-level","title":"EmotionFlow: Capture the Dialogue Level Emotion Transitions","date":"2022-05-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"number-entity-recognition","title":"Improving Downstream Task Performance by Treating Numbers as Entities","date":"2022-05-07","arxiv_id":"2205.03559","n_code_links":0,"syntology":null},{"paper":null,"slug":"vector-representations-of-idioms-in","title":"Vector Representations of Idioms in Conversational Systems","date":"2022-05-07","arxiv_id":"2205.03666","n_code_links":0,"syntology":null},{"paper":"/paper/a-data-cartography-based-mixup-for-pre","slug":"a-data-cartography-based-mixup-for-pre","title":"A Data Cartography based MixUp for Pre-trained Language Models","date":"2022-05-06","arxiv_id":"2205.03403","n_code_links":1,"syntology":null},{"paper":"/paper/stock-price-prediction-based-on-natural","slug":"stock-price-prediction-based-on-natural","title":"Stock Price Prediction Based on Natural Language Processing","date":"2022-05-06","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/the-unreliability-of-explanations-in-few-shot","slug":"the-unreliability-of-explanations-in-few-shot","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","date":"2022-05-06","arxiv_id":"2205.03401","n_code_links":1,"syntology":null},{"paper":"/paper/when-a-sentence-does-not-introduce-a-1","slug":"when-a-sentence-does-not-introduce-a-1","title":"When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it","date":"2022-05-06","arxiv_id":"2205.03472","n_code_links":1,"syntology":null},{"paper":"/paper/bort-back-and-denoising-reconstruction-for-1","slug":"bort-back-and-denoising-reconstruction-for-1","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2022-05-05","arxiv_id":"2205.02471","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-global-and-local-hierarchies-for","slug":"exploiting-global-and-local-hierarchies-for","title":"Exploiting Global and Local Hierarchies for Hierarchical Text Classification","date":"2022-05-05","arxiv_id":"2205.02613","n_code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-relevance-matching-for-neural","slug":"hyperbolic-relevance-matching-for-neural","title":"Hyperbolic Relevance Matching for Neural Keyphrase Extraction","date":"2022-05-04","arxiv_id":"2205.02047","n_code_links":1,"syntology":null},{"paper":"/paper/provably-confidential-language-modelling-1","slug":"provably-confidential-language-modelling-1","title":"Provably Confidential Language Modelling","date":"2022-05-04","arxiv_id":"2205.01863","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":["xuandongzhao/crt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"using-virtual-edges-to-extract-keywords-from","title":"Using virtual edges to extract keywords from texts modeled as complex networks","date":"2022-05-04","arxiv_id":"2205.02172","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-learning-for-prompt-based-few","slug":"contrastive-learning-for-prompt-based-few","title":"Contrastive Learning for Prompt-Based Few-Shot Language Learners","date":"2022-05-03","arxiv_id":"2205.01308","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["yiren-jian/lm-supcon"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-fine-tuning-of-bert-models-on-the","title":"Efficient Fine-Tuning of BERT Models on the Edge","date":"2022-05-03","arxiv_id":"2205.01541","n_code_links":0,"syntology":null},{"paper":null,"slug":"explain-and-conquer-personalised-text-based","title":"Explain and Conquer: Personalised Text-based Reviews to Achieve Transparency","date":"2022-05-03","arxiv_id":"2205.01759","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-patterns-in-knowledge-attribution-for","title":"Finding patterns in Knowledge Attribution for Transformers","date":"2022-05-03","arxiv_id":"2205.01366","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-effects-transformers-for-hierarchical","slug":"mixed-effects-transformers-for-hierarchical","title":"Mixed-effects transformers for hierarchical adaptation","date":"2022-05-03","arxiv_id":"2205.01749","n_code_links":1,"syntology":null},{"paper":"/paper/predicting-issue-types-with-sebert","slug":"predicting-issue-types-with-sebert","title":"Predicting Issue Types with seBERT","date":"2022-05-03","arxiv_id":"2205.01335","n_code_links":1,"syntology":null},{"paper":"/paper/semattack-natural-textual-attacks-via-1","slug":"semattack-natural-textual-attacks-via-1","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-05-03","arxiv_id":"2205.01287","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai-secure/semattack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertops-studying-bert-representations-under-a","slug":"bertops-studying-bert-representations-under-a","title":"BERTops: Studying BERT Representations under a Topological Lens","date":"2022-05-02","arxiv_id":"2205.00953","n_code_links":1,"syntology":null},{"paper":"/paper/entity-aware-transformers-for-entity-search","slug":"entity-aware-transformers-for-entity-search","title":"Entity-aware Transformers for Entity Search","date":"2022-05-02","arxiv_id":"2205.00820","n_code_links":1,"syntology":null},{"paper":"/paper/improving-students-academic-performance-with","slug":"improving-students-academic-performance-with","title":"Improving Students' Academic Performance with AI and Semantic Technologies","date":"2022-05-02","arxiv_id":"2206.03213","n_code_links":1,"syntology":null},{"paper":"/paper/opt-open-pre-trained-transformer-language","slug":"opt-open-pre-trained-transformer-language","title":"OPT: Open Pre-trained Transformer Language Models","date":"2022-05-02","arxiv_id":"2205.01068","n_code_links":11,"syntology":{"ran":14,"of":24,"n_ran_checked":14,"n_instrument":0,"unverified":10,"pointer_only":17,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["facebookresearch/metaseq"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"detecting-covid-19-conspiracy-theories-with","title":"Detecting COVID-19 Conspiracy Theories with Transformers and TF-IDF","date":"2022-05-01","arxiv_id":"2205.00377","n_code_links":0,"syntology":null},{"paper":"/paper/storseismic-a-new-paradigm-in-deep-learning","slug":"storseismic-a-new-paradigm-in-deep-learning","title":"StorSeismic: A new paradigm in deep learning for seismic processing","date":"2022-04-30","arxiv_id":"2205.00222","n_code_links":1,"syntology":null},{"paper":"/paper/exaasc-a-general-target-based-stance","slug":"exaasc-a-general-target-based-stance","title":"ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language","date":"2022-04-29","arxiv_id":"2204.13979","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-from-natural-language-feedback","title":"Training Language Models with Language Feedback","date":"2022-04-29","arxiv_id":"2204.14146","n_code_links":0,"syntology":null},{"paper":null,"slug":"qrelscore-better-evaluating-generated","title":"QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance","date":"2022-04-29","arxiv_id":"2204.13921","n_code_links":0,"syntology":null},{"paper":"/paper/two-new-datasets-for-italian-language","slug":"two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","date":"2022-04-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/hiner-a-large-hindi-named-entity-recognition","slug":"hiner-a-large-hindi-named-entity-recognition","title":"HiNER: A Large Hindi Named Entity Recognition Dataset","date":"2022-04-28","arxiv_id":"2204.13743","n_code_links":1,"syntology":null},{"paper":"/paper/inferring-implicit-relations-with-language","slug":"inferring-implicit-relations-with-language","title":"Inferring Implicit Relations in Complex Questions with Language Models","date":"2022-04-28","arxiv_id":"2204.13778","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-effect-of-pretraining-corpora-on-in","title":"On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model","date":"2022-04-28","arxiv_id":"2204.13509","n_code_links":0,"syntology":null},{"paper":null,"slug":"robbertje-a-distilled-dutch-bert-model","title":"RobBERTje: a Distilled Dutch BERT Model","date":"2022-04-28","arxiv_id":"2204.13511","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailor-a-prompt-based-approach-to-attribute","title":"Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation","date":"2022-04-28","arxiv_id":"2204.13362","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-end-to-end-dialogue-summarization-system","title":"An End-to-End Dialogue Summarization System for Sales Calls","date":"2022-04-27","arxiv_id":"2204.12951","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-query-graph-selection-for-knowledge","title":"Better Query Graph Selection for Knowledge Base Question Answering","date":"2022-04-27","arxiv_id":"2204.12662","n_code_links":0,"syntology":null},{"paper":"/paper/modern-baselines-for-sparql-semantic-parsing","slug":"modern-baselines-for-sparql-semantic-parsing","title":"Modern Baselines for SPARQL Semantic Parsing","date":"2022-04-27","arxiv_id":"2204.12793","n_code_links":1,"syntology":null},{"paper":null,"slug":"rigoberta-a-state-of-the-art-language-model","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","date":"2022-04-27","arxiv_id":"2205.10233","n_code_links":0,"syntology":null},{"paper":"/paper/skillspan-hard-and-soft-skill-extraction-from","slug":"skillspan-hard-and-soft-skill-extraction-from","title":"SkillSpan: Hard and Soft Skill Extraction from English Job Postings","date":"2022-04-27","arxiv_id":"2204.12811","n_code_links":1,"syntology":null},{"paper":null,"slug":"timebert-enhancing-pre-trained-language","title":"BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information","date":"2022-04-27","arxiv_id":"2204.13032","n_code_links":0,"syntology":null},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","n_code_links":1,"syntology":null},{"paper":"/paper/plod-an-abbreviation-detection-dataset-for","slug":"plod-an-abbreviation-detection-dataset-for","title":"PLOD: An Abbreviation Detection Dataset for Scientific Documents","date":"2022-04-26","arxiv_id":"2204.12061","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretraining-chinese-bert-for-detecting-word","title":"Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors","date":"2022-04-26","arxiv_id":"2204.12052","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-extrapolation-performance-of-dense","slug":"evaluating-extrapolation-performance-of-dense","title":"Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models","date":"2022-04-25","arxiv_id":"2204.11447","n_code_links":1,"syntology":null},{"paper":"/paper/groupwise-query-performance-prediction-with","slug":"groupwise-query-performance-prediction-with","title":"Groupwise Query Performance Prediction with BERT","date":"2022-04-25","arxiv_id":"2204.11489","n_code_links":1,"syntology":null},{"paper":"/paper/faster-learned-sparse-retrieval-with-guided","slug":"faster-learned-sparse-retrieval-with-guided","title":"Faster Learned Sparse Retrieval with Guided Traversal","date":"2022-04-24","arxiv_id":"2204.11314","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-win-lottery-tickets-in-bert-1","slug":"learning-to-win-lottery-tickets-in-bert-1","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","date":"2022-04-24","arxiv_id":"2204.11218","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-models-to-classify","title":"Fine-Tuning BERT Models to Classify Misinformation on Garlic and COVID-19 on Twitter","date":"2022-04-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taygete-at-semeval-2022-task-4-roberta-based","title":"Taygete at SemEval-2022 Task 4: RoBERTa based models for detecting Patronising and Condescending Language","date":"2022-04-22","arxiv_id":"2204.10519","n_code_links":0,"syntology":null},{"paper":null,"slug":"wabert-a-low-resource-end-to-end-model-for","title":"WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment","date":"2022-04-22","arxiv_id":"2204.10461","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-artificial-intelligence-as-a","title":"Measuring artificial intelligence: a systematic assessment and implications for governance","date":"2022-04-21","arxiv_id":"2204.10304","n_code_links":0,"syntology":null},{"paper":"/paper/is-neural-topic-modelling-better-than-1","slug":"is-neural-topic-modelling-better-than-1","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","date":"2022-04-21","arxiv_id":"2204.09874","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hyintell/topicx"],"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":"/paper/is-bert-robust-to-label-noise-a-study-on","slug":"is-bert-robust-to-label-noise-a-study-on","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","date":"2022-04-20","arxiv_id":"2204.09371","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uds-lsv/bert-lnl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-arabic-sentence-simplification-via","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","date":"2022-04-20","arxiv_id":"2204.09292","n_code_links":0,"syntology":null},{"paper":"/paper/albeto-and-distilbeto-lightweight-spanish","slug":"albeto-and-distilbeto-lightweight-spanish","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","date":"2022-04-19","arxiv_id":"2204.09145","n_code_links":2,"syntology":null},{"paper":null,"slug":"codexdb-generating-code-for-processing-sql","title":"CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex","date":"2022-04-19","arxiv_id":"2204.08941","n_code_links":0,"syntology":null},{"paper":null,"slug":"decbert-enhancing-the-language-understanding","title":"DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks","date":"2022-04-19","arxiv_id":"2204.08688","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an-1","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2022-04-19","arxiv_id":"2204.08832","n_code_links":0,"syntology":null},{"paper":"/paper/litmc-bert-transformer-based-multi-label","slug":"litmc-bert-transformer-based-multi-label","title":"LitMC-BERT: transformer-based multi-label classification of biomedical literature with an application on COVID-19 literature curation","date":"2022-04-19","arxiv_id":"2204.08649","n_code_links":1,"syntology":null},{"paper":null,"slug":"mono-vs-multilingual-bert-for-hate-speech","title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi","date":"2022-04-19","arxiv_id":"2204.08669","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-hate-speech-detection-from-bengali","slug":"multimodal-hate-speech-detection-from-bengali","title":"Multimodal Hate Speech Detection from Bengali Memes and Texts","date":"2022-04-19","arxiv_id":"2204.10196","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-for-the-usage-of-grammatical-number","title":"Probing for the Usage of Grammatical Number","date":"2022-04-19","arxiv_id":"2204.08831","n_code_links":0,"syntology":null},{"paper":"/paper/ingredient-extraction-from-text-in-the-recipe","slug":"ingredient-extraction-from-text-in-the-recipe","title":"Ingredient Extraction from Text in the Recipe Domain","date":"2022-04-18","arxiv_id":"2204.08137","n_code_links":1,"syntology":null},{"paper":"/paper/l3cube-hingcorpus-and-hingbert-a-code-mixed","slug":"l3cube-hingcorpus-and-hingbert-a-code-mixed","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","date":"2022-04-18","arxiv_id":"2204.08398","n_code_links":1,"syntology":null},{"paper":"/paper/massive-a-1m-example-multilingual-natural","slug":"massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","n_code_links":6,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alexa/massive"],"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":["listed","official"]}}},{"paper":"/paper/utnlp-at-semeval-2022-task-6-a-comparative","slug":"utnlp-at-semeval-2022-task-6-a-comparative","title":"UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation","date":"2022-04-18","arxiv_id":"2204.08198","n_code_links":2,"syntology":null},{"paper":null,"slug":"zero-shot-entity-and-tweet-characterization","title":"Zero-shot Entity and Tweet Characterization with Designed Conditional Prompts and Contexts","date":"2022-04-18","arxiv_id":"2204.08405","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-effectively-learning-of-knowledge-in","title":"Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base","date":"2022-04-17","arxiv_id":"2204.07994","n_code_links":0,"syntology":null},{"paper":null,"slug":"pathologies-of-pre-trained-language-models-in","title":"Pathologies of Pre-trained Language Models in Few-shot Fine-tuning","date":"2022-04-17","arxiv_id":"2204.08039","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-script-knowledge-from-pre-trained","title":"Probing Script Knowledge from Pre-Trained Models","date":"2022-04-16","arxiv_id":"2204.10176","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplebert-a-pre-trained-model-that-learns-to","title":"SimpleBERT: A Pre-trained Model That Learns to Generate Simple Words","date":"2022-04-16","arxiv_id":"2204.07779","n_code_links":0,"syntology":null},{"paper":null,"slug":"wordalchemy-a-transformer-based-reverse","title":"WordAlchemy: A transformer-based Reverse Dictionary","date":"2022-04-16","arxiv_id":"2204.10181","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-language-models-with","title":"Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition","date":"2022-04-15","arxiv_id":"2204.07464","n_code_links":0,"syntology":null},{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","n_code_links":1,"syntology":null},{"paper":null,"slug":"ml-ltu-at-semeval-2022-task-4-t5-towards","title":"ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language","date":"2022-04-15","arxiv_id":"2204.07432","n_code_links":0,"syntology":null},{"paper":"/paper/polling-latent-opinions-a-method-for-1","slug":"polling-latent-opinions-a-method-for-1","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-04-15","arxiv_id":"2204.07483","n_code_links":1,"syntology":null},{"paper":null,"slug":"resource-aware-distributed-submodular","title":"Resource-Aware Distributed Submodular Maximization: A Paradigm for Multi-Robot Decision-Making","date":"2022-04-15","arxiv_id":"2204.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"brazilian-court-documents-clustered-by","title":"Analysing similarities between legal court documents using natural language processing approaches based on Transformers","date":"2022-04-14","arxiv_id":"2204.07182","n_code_links":0,"syntology":null},{"paper":"/paper/calbert-code-mixed-adaptive-language-1","slug":"calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"does-bert-really-agree-fine-grained-analysis-1","title":"Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task","date":"2022-04-14","arxiv_id":"2204.06889","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","n_code_links":11,"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":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/latent-aspect-detection-from-online","slug":"latent-aspect-detection-from-online","title":"Latent Aspect Detection from Online Unsolicited Customer Reviews","date":"2022-04-14","arxiv_id":"2204.06964","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-label-topic-classification-for-covid-19","title":"Multi-label topic classification for COVID-19 literature with Bioformer","date":"2022-04-14","arxiv_id":"2204.06758","n_code_links":0,"syntology":null},{"paper":null,"slug":"rows-from-many-sources-enriching-row","title":"Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model","date":"2022-04-14","arxiv_id":"2204.07014","n_code_links":0,"syntology":null},{"paper":"/paper/vitol-vision-transformer-for-weakly","slug":"vitol-vision-transformer-for-weakly","title":"ViTOL: Vision Transformer for Weakly Supervised Object Localization","date":"2022-04-14","arxiv_id":"2204.06772","n_code_links":1,"syntology":null},{"paper":"/paper/hubert-ee-early-exiting-hubert-for-efficient","slug":"hubert-ee-early-exiting-hubert-for-efficient","title":"HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition","date":"2022-04-13","arxiv_id":"2204.06328","n_code_links":1,"syntology":null},{"paper":null,"slug":"iiitdwd-shankarb-dravidian-codemixi-hasoc2021","title":"IIITDWD-ShankarB@ Dravidian-CodeMixi-HASOC2021: mBERT based model for identification of offensive content in south Indian languages","date":"2022-04-13","arxiv_id":"2204.10195","n_code_links":0,"syntology":null},{"paper":null,"slug":"metro-efficient-denoising-pretraining-of","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","date":"2022-04-13","arxiv_id":"2204.06644","n_code_links":0,"syntology":null},{"paper":"/paper/probing-for-constituency-structure-in-neural","slug":"probing-for-constituency-structure-in-neural","title":"Probing for Constituency Structure in Neural Language Models","date":"2022-04-13","arxiv_id":"2204.06201","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["davidarps/constptbprobing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"6ec006a01c4848d33811032f6ee6a8cc162ea5416e4d2516e4fae085771bd45c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}