{"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/86","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":86,"pages_in_order":109,"rows_per_page":100,"rows":[8501,8600],"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/85","next":"/method/attention-dropout/papers/87","papers":[{"paper":null,"slug":"modeling-newsworthiness-for-lead-generation","title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora","date":"2021-04-19","arxiv_id":"2104.09653","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-language-models-with-distant","title":"Neural Language Models with Distant Supervision to Identify Major Depressive Disorder from Clinical Notes","date":"2021-04-19","arxiv_id":"2104.09644","n_code_links":0,"syntology":null},{"paper":"/paper/octis-comparing-and-optimizing-topic-models","slug":"octis-comparing-and-optimizing-topic-models","title":"OCTIS: Comparing and Optimizing Topic models is Simple!","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/operationalizing-a-national-digital-library","slug":"operationalizing-a-national-digital-library","title":"Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model","date":"2021-04-19","arxiv_id":"2104.09617","n_code_links":2,"syntology":null},{"paper":"/paper/probing-for-bridging-inference-in-transformer","slug":"probing-for-bridging-inference-in-transformer","title":"Probing for Bridging Inference in Transformer Language Models","date":"2021-04-19","arxiv_id":"2104.09400","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-classification-in-swahili-language","title":"Sentiment Classification in Swahili Language Using Multilingual BERT","date":"2021-04-19","arxiv_id":"2104.09006","n_code_links":0,"syntology":null},{"paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","slug":"teamuncc-lt-edi-eacl2021-hope-speech","title":"TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-token-level-reference-free-hallucination","slug":"a-token-level-reference-free-hallucination","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","date":"2021-04-18","arxiv_id":"2104.08704","n_code_links":2,"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":["microsoft/HaDes"],"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":"cear-cross-entity-aware-reranker-for","title":"CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion","date":"2021-04-18","arxiv_id":"2104.08741","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-view-distilled-bert-for-sentence","title":"Dual-View Distilled BERT for Sentence Embedding","date":"2021-04-18","arxiv_id":"2104.08675","n_code_links":0,"syntology":null},{"paper":"/paper/fantastically-ordered-prompts-and-where-to","slug":"fantastically-ordered-prompts-and-where-to","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","date":"2021-04-18","arxiv_id":"2104.08786","n_code_links":2,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/fednlp-a-research-platform-for-federated","slug":"fednlp-a-research-platform-for-federated","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","date":"2021-04-18","arxiv_id":"2104.08815","n_code_links":1,"syntology":null},{"paper":"/paper/gpt3mix-leveraging-large-scale-language","slug":"gpt3mix-leveraging-large-scale-language","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","date":"2021-04-18","arxiv_id":"2104.08826","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":["naver-ai/hypermix"],"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/knowledge-neurons-in-pretrained-transformers","slug":"knowledge-neurons-in-pretrained-transformers","title":"Knowledge Neurons in Pretrained Transformers","date":"2021-04-18","arxiv_id":"2104.08696","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hunter-ddm/knowledge-neurons"],"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":["listed","official"]}}},{"paper":null,"slug":"language-in-a-search-box-grounding-language","title":"Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction","date":"2021-04-18","arxiv_id":"2104.08874","n_code_links":0,"syntology":null},{"paper":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","n_code_links":2,"syntology":null},{"paper":"/paper/natural-instructions-benchmarking","slug":"natural-instructions-benchmarking","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","date":"2021-04-18","arxiv_id":"2104.08773","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/natural-instructions","allenai/natural-instructions-v1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/rethinking-network-pruning-under-the-pre","slug":"rethinking-network-pruning-under-the-pre","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","date":"2021-04-18","arxiv_id":"2104.08682","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["derronxu/sparsebert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/simcse-simple-contrastive-learning-of","slug":"simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","arxiv_id":"2104.08821","n_code_links":23,"syntology":{"ran":17,"of":30,"n_ran_checked":12,"n_instrument":5,"unverified":13,"pointer_only":19,"phrase":"17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","official":{"repos":["princeton-nlp/SimCSE"],"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/the-power-of-scale-for-parameter-efficient","slug":"the-power-of-scale-for-parameter-efficient","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","date":"2021-04-18","arxiv_id":"2104.08691","n_code_links":12,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/prompt-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":"/paper/zero-shot-cross-lingual-transfer-of-neural","slug":"zero-shot-cross-lingual-transfer-of-neural","title":"Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders","date":"2021-04-18","arxiv_id":"2104.08757","n_code_links":1,"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":["ghchen18/emnlp2021-sixt"],"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":"a-multilabel-approach-to-morphosyntactic","title":"A multilabel approach to morphosyntactic probing","date":"2021-04-17","arxiv_id":"2104.08464","n_code_links":0,"syntology":null},{"paper":null,"slug":"asbert-siamese-and-triplet-network-embedding","title":"ASBERT: Siamese and Triplet network embedding for open question answering","date":"2021-04-17","arxiv_id":"2104.08558","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-bert-a-context-aware-bert-retrieval-model","title":"Co-BERT: A Context-Aware BERT Retrieval Model Incorporating Local and Query-specific Context","date":"2021-04-17","arxiv_id":"2104.08523","n_code_links":0,"syntology":null},{"paper":"/paper/decrypting-cryptic-crosswords-semantically","slug":"decrypting-cryptic-crosswords-semantically","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","date":"2021-04-17","arxiv_id":"2104.08620","n_code_links":2,"syntology":null},{"paper":null,"slug":"frequency-based-distortions-in-contextualized","title":"Frequency-based Distortions in Contextualized Word Embeddings","date":"2021-04-17","arxiv_id":"2104.08465","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-transformer-networks-for","slug":"hierarchical-transformer-networks-for","title":"Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-04-17","arxiv_id":"2104.08444","n_code_links":1,"syntology":null},{"paper":"/paper/identifying-the-limits-of-cross-domain","slug":"identifying-the-limits-of-cross-domain","title":"Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models","date":"2021-04-17","arxiv_id":"2104.08410","n_code_links":1,"syntology":null},{"paper":"/paper/improving-zero-shot-cross-lingual-transfer","slug":"improving-zero-shot-cross-lingual-transfer","title":"Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training","date":"2021-04-17","arxiv_id":"2104.08645","n_code_links":1,"syntology":null},{"paper":"/paper/multi-source-neural-topic-modeling-in-multi","slug":"multi-source-neural-topic-modeling-in-multi","title":"Multi-source Neural Topic Modeling in Multi-view Embedding Spaces","date":"2021-04-17","arxiv_id":"2104.08551","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-topic-confusion-task-a-novel-scenario-for","title":"The Topic Confusion Task: A Novel Scenario for Authorship Attribution","date":"2021-04-17","arxiv_id":"2104.08530","n_code_links":0,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2021-task-5-virtual","title":"UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection","date":"2021-04-17","arxiv_id":"2104.08635","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-slot-filling-with-dpr-and-rag","slug":"zero-shot-slot-filling-with-dpr-and-rag","title":"Zero-shot Slot Filling with DPR and RAG","date":"2021-04-17","arxiv_id":"2104.08610","n_code_links":2,"syntology":null},{"paper":"/paper/an-adversarially-learned-turing-test-for","slug":"an-adversarially-learned-turing-test-for","title":"An Adversarially-Learned Turing Test for Dialog Generation Models","date":"2021-04-16","arxiv_id":"2104.08231","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-a-bert-deep-learning-strategy","title":"An Analysis of a BERT Deep Learning Strategy on a Technology Assisted Review Task","date":"2021-04-16","arxiv_id":"2104.08340","n_code_links":0,"syntology":null},{"paper":"/paper/bert-memorisation-and-pitfalls-in-low","slug":"bert-memorisation-and-pitfalls-in-low","title":"Memorisation versus Generalisation in Pre-trained Language Models","date":"2021-04-16","arxiv_id":"2105.00828","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["Michael-Tanzer/BERT-mem-lowres"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/editing-factual-knowledge-in-language-models","slug":"editing-factual-knowledge-in-language-models","title":"Editing Factual Knowledge in Language Models","date":"2021-04-16","arxiv_id":"2104.08164","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nicola-decao/KnowledgeEditor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fast-effective-and-self-supervised","slug":"fast-effective-and-self-supervised","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","date":"2021-04-16","arxiv_id":"2104.08027","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["cambridgeltl/mirror-bert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"membership-inference-attack-susceptibility-of","title":"Membership Inference Attack Susceptibility of Clinical Language Models","date":"2021-04-16","arxiv_id":"2104.08305","n_code_links":0,"syntology":null},{"paper":"/paper/probing-across-time-what-does-roberta-know","slug":"probing-across-time-what-does-roberta-know","title":"Probing Across Time: What Does RoBERTa Know and When?","date":"2021-04-16","arxiv_id":"2104.07885","n_code_links":1,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["leo-liuzy/probe-across-time"],"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/surface-form-competition-why-the-highest","slug":"surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","date":"2021-04-16","arxiv_id":"2104.08315","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peterwestuw/surface-form-competition"],"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/temporal-adaptation-of-bert-and-performance","slug":"temporal-adaptation-of-bert-and-performance","title":"Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media","date":"2021-04-16","arxiv_id":"2104.08116","n_code_links":2,"syntology":null},{"paper":"/paper/text2app-a-framework-for-creating-android","slug":"text2app-a-framework-for-creating-android","title":"Text2App: A Framework for Creating Android Apps from Text Descriptions","date":"2021-04-16","arxiv_id":"2104.08301","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-variable-length-textual-adversarial","title":"Towards Variable-Length Textual Adversarial Attacks","date":"2021-04-16","arxiv_id":"2104.08139","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sample-based-training-method-for-distantly","title":"A Sample-Based Training Method for Distantly Supervised Relation Extraction with Pre-Trained Transformers","date":"2021-04-15","arxiv_id":"2104.07512","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-recent-abstract-summarization","title":"A Survey of Recent Abstract Summarization Techniques","date":"2021-04-15","arxiv_id":"2105.00824","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-multilingual-bert-models-robust-a-case","title":"Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering","date":"2021-04-15","arxiv_id":"2104.07646","n_code_links":0,"syntology":null},{"paper":"/paper/bert-based-transformers-lead-the-way-in","slug":"bert-based-transformers-lead-the-way-in","title":"BERT based Transformers lead the way in Extraction of Health Information from Social Media","date":"2021-04-15","arxiv_id":"2104.07367","n_code_links":1,"syntology":null},{"paper":"/paper/does-bert-pretrained-on-clinical-notes-reveal","slug":"does-bert-pretrained-on-clinical-notes-reveal","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","date":"2021-04-15","arxiv_id":"2104.07762","n_code_links":4,"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":["elehman16/exposing_patient_data_release"],"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":"emotion-dynamics-modeling-via-bert","title":"Emotion Dynamics Modeling via BERT","date":"2021-04-15","arxiv_id":"2104.07252","n_code_links":0,"syntology":null},{"paper":"/paper/explagraphs-an-explanation-graph-generation","slug":"explagraphs-an-explanation-graph-generation","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","date":"2021-04-15","arxiv_id":"2104.07644","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["swarnaHub/ExplaGraphs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-to-train-bert-with-an-academic-budget","slug":"how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","date":"2021-04-15","arxiv_id":"2104.07705","n_code_links":4,"syntology":null},{"paper":"/paper/nt5-training-t5-to-perform-numerical","slug":"nt5-training-t5-to-perform-numerical","title":"NT5?! Training T5 to Perform Numerical Reasoning","date":"2021-04-15","arxiv_id":"2104.07307","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-adaptive-bert-for-natural-language","title":"Natural Language Understanding with Privacy-Preserving BERT","date":"2021-04-15","arxiv_id":"2104.07504","n_code_links":0,"syntology":null},{"paper":null,"slug":"sina-bert-a-pre-trained-language-model-for","title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","date":"2021-04-15","arxiv_id":"2104.07613","n_code_links":0,"syntology":null},{"paper":"/paper/text-guide-improving-the-quality-of-long-text","slug":"text-guide-improving-the-quality-of-long-text","title":"Text Guide: Improving the quality of long text classification by a text selection method based on feature importance","date":"2021-04-15","arxiv_id":"2104.07225","n_code_links":1,"syntology":null},{"paper":"/paper/torontocl-at-cmcl-2021-shared-task-roberta","slug":"torontocl-at-cmcl-2021-shared-task-roberta","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","date":"2021-04-15","arxiv_id":"2104.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"uhd-bert-bucketed-ultra-high-dimensional","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","date":"2021-04-15","arxiv_id":"2104.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"uit-e10dot3-at-semeval-2021-task-5-toxic","title":"UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches","date":"2021-04-15","arxiv_id":"2104.07376","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-interpretability-illusion-for-bert","title":"An Interpretability Illusion for BERT","date":"2021-04-14","arxiv_id":"2104.07143","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystifying-bert-implications-for","title":"Demystifying BERT: Implications for Accelerator Design","date":"2021-04-14","arxiv_id":"2104.08335","n_code_links":0,"syntology":null},{"paper":null,"slug":"dependency-parsing-based-semantic","title":"Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis","date":"2021-04-14","arxiv_id":"2104.06835","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-representations-of-text-by-1","title":"Disentangling Representations of Text by Masking Transformers","date":"2021-04-14","arxiv_id":"2104.07155","n_code_links":0,"syntology":null},{"paper":"/paper/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-robustness-of-goal-oriented-dialogue","slug":"on-the-robustness-of-goal-oriented-dialogue","title":"On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise","date":"2021-04-14","arxiv_id":"2104.07149","n_code_links":1,"syntology":null},{"paper":"/paper/static-embeddings-as-efficient-knowledge","slug":"static-embeddings-as-efficient-knowledge","title":"Static Embeddings as Efficient Knowledge Bases?","date":"2021-04-14","arxiv_id":"2104.07094","n_code_links":1,"syntology":null},{"paper":"/paper/1-bit-lamb-communication-efficient-large","slug":"1-bit-lamb-communication-efficient-large","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","date":"2021-04-13","arxiv_id":"2104.06069","n_code_links":1,"syntology":null},{"paper":"/paper/discourse-probing-of-pretrained-language","slug":"discourse-probing-of-pretrained-language","title":"Discourse Probing of Pretrained Language Models","date":"2021-04-13","arxiv_id":"2104.05882","n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-contextualised-language-modelling","slug":"large-scale-contextualised-language-modelling","title":"Large-Scale Contextualised Language Modelling for Norwegian","date":"2021-04-13","arxiv_id":"2104.06546","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ltgoslo/NorBERT","ltgoslo/norec_sentence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mediators-in-determining-what-processing-bert","slug":"mediators-in-determining-what-processing-bert","title":"Mediators in Determining what Processing BERT Performs First","date":"2021-04-13","arxiv_id":"2104.06400","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-maps-and-metrics-for-science","title":"Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders","date":"2021-04-13","arxiv_id":"2104.05928","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-freedom-to-operate-patent-analysis","title":"BERT based freedom to operate patent analysis","date":"2021-04-12","arxiv_id":"2105.00817","n_code_links":0,"syntology":null},{"paper":"/paper/fighting-the-covid-19-infodemic-with-a","slug":"fighting-the-covid-19-infodemic-with-a","title":"Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble","date":"2021-04-12","arxiv_id":"2104.05745","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-transformers-for-identifying-self","slug":"fine-tuning-transformers-for-identifying-self","title":"Fine-Tuning Transformers for Identifying Self-Reporting Potential Cases and Symptoms of COVID-19 in Tweets","date":"2021-04-12","arxiv_id":"2104.05501","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-remove-towards-isotropic-pre","slug":"learning-to-remove-towards-isotropic-pre","title":"Learning to Remove: Towards Isotropic Pre-trained BERT Embedding","date":"2021-04-12","arxiv_id":"2104.05274","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-language-models-predict-human","slug":"multilingual-language-models-predict-human","title":"Multilingual Language Models Predict Human Reading Behavior","date":"2021-04-12","arxiv_id":"2104.05433","n_code_links":1,"syntology":null},{"paper":"/paper/whose-heritage-classification-of-unesco-world","slug":"whose-heritage-classification-of-unesco-world","title":"WHOSe Heritage: Classification of UNESCO World Heritage \"Outstanding Universal Value\" Documents with Soft Labels","date":"2021-04-12","arxiv_id":"2104.05547","n_code_links":1,"syntology":null},{"paper":"/paper/does-syntax-matter-a-strong-baseline-for","slug":"does-syntax-matter-a-strong-baseline-for","title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","date":"2021-04-11","arxiv_id":"2104.04986","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-encoders-for-improved-monolingual","slug":"fine-tuning-encoders-for-improved-monolingual","title":"Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling","date":"2021-04-11","arxiv_id":"2104.05064","n_code_links":1,"syntology":null},{"paper":null,"slug":"innovative-bert-based-reranking-language","title":"Innovative Bert-based Reranking Language Models for Speech Recognition","date":"2021-04-11","arxiv_id":"2104.04950","n_code_links":0,"syntology":null},{"paper":"/paper/unidrop-a-simple-yet-effective-technique-to","slug":"unidrop-a-simple-yet-effective-technique-to","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","date":"2021-04-11","arxiv_id":"2104.04946","n_code_links":0,"syntology":null},{"paper":"/paper/meta-tuning-language-models-to-answer-prompts","slug":"meta-tuning-language-models-to-answer-prompts","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","date":"2021-04-10","arxiv_id":"2104.04670","n_code_links":1,"syntology":null},{"paper":"/paper/mipt-nsu-utmn-at-semeval-2021-task-5","slug":"mipt-nsu-utmn-at-semeval-2021-task-5","title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","date":"2021-04-10","arxiv_id":"2104.04739","n_code_links":1,"syntology":null},{"paper":null,"slug":"non-autoregressive-transformer-based-end-to","title":"Non-autoregressive Transformer-based End-to-end ASR using BERT","date":"2021-04-10","arxiv_id":"2104.04805","n_code_links":0,"syntology":null},{"paper":"/paper/zs-bert-towards-zero-shot-relation-extraction","slug":"zs-bert-towards-zero-shot-relation-extraction","title":"ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning","date":"2021-04-10","arxiv_id":"2104.04697","n_code_links":1,"syntology":null},{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":"/paper/know-what-and-know-where-an-object-and-room","slug":"know-what-and-know-where-an-object-and-room","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","date":"2021-04-09","arxiv_id":"2104.04167","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":"/paper/text2chart-a-multi-staged-chart-generator","slug":"text2chart-a-multi-staged-chart-generator","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","date":"2021-04-09","arxiv_id":"2104.04584","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-the-end-of-history-for-nlp","title":"Transformers: \"The End of History\" for NLP?","date":"2021-04-09","arxiv_id":"2105.00813","n_code_links":0,"syntology":null},{"paper":"/paper/lone-pine-at-semeval-2021-task-5-fine-grained","slug":"lone-pine-at-semeval-2021-task-5-fine-grained","title":"Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic","date":"2021-04-08","arxiv_id":"2104.03506","n_code_links":1,"syntology":null},{"paper":"/paper/probing-bert-in-hyperbolic-spaces-1","slug":"probing-bert-in-hyperbolic-spaces-1","title":"Probing BERT in Hyperbolic Spaces","date":"2021-04-08","arxiv_id":"2104.03869","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["FranxYao/PoincareProbe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uppsala-nlp-at-semeval-2021-task-2","title":"Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation","date":"2021-04-08","arxiv_id":"2104.03767","n_code_links":0,"syntology":null},{"paper":"/paper/better-neural-machine-translation-by","slug":"better-neural-machine-translation-by","title":"Better Neural Machine Translation by Extracting Linguistic Information from BERT","date":"2021-04-07","arxiv_id":"2104.02831","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-pre-trained-word-embeddings-and","title":"Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identification","date":"2021-04-07","arxiv_id":"2104.03285","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-verbal-metaphors-by-paraphrasing","title":"Interpreting Verbal Metaphors by Paraphrasing","date":"2021-04-07","arxiv_id":"2104.03391","n_code_links":0,"syntology":null},{"paper":"/paper/speak-or-chat-with-me-end-to-end-spoken","slug":"speak-or-chat-with-me-end-to-end-spoken","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","date":"2021-04-07","arxiv_id":"2104.05752","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-evaluation-of-word-embedding","slug":"an-empirical-evaluation-of-word-embedding","title":"An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks","date":"2021-04-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/codetrans-towards-cracking-the-language-of","slug":"codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","n_code_links":1,"syntology":null}],"record_sha256":"559cc04aa7b5a55bb799222668efc250764f94ddd5411b87fd6771b37a639b00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}