{"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/102","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":102,"pages_in_order":109,"rows_per_page":100,"rows":[10101,10200],"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/101","next":"/method/attention-dropout/papers/103","papers":[{"paper":null,"slug":"cascade-neural-ensemble-for-identifying","title":"Cascade Neural Ensemble for Identifying Scientifically Sound Articles","date":"2020-04-13","arxiv_id":"2004.06222","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-scholarly-knowledge-representation","title":"Improving Scholarly Knowledge Representation: Evaluating BERT-based Models for Scientific Relation Classification","date":"2020-04-13","arxiv_id":"2004.06153","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-transformers-improve-out-of","slug":"pretrained-transformers-improve-out-of","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","date":"2020-04-13","arxiv_id":"2004.06100","n_code_links":1,"syntology":null},{"paper":null,"slug":"proformer-towards-on-device-lsh-projection","title":"ProFormer: Towards On-Device LSH Projection Based Transformers","date":"2020-04-13","arxiv_id":"2004.05801","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustly-pre-trained-neural-model-for-direct","title":"Robustly Pre-trained Neural Model for Direct Temporal Relation Extraction","date":"2020-04-13","arxiv_id":"2004.06216","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-multi-criteria-chinese-word","title":"Unified Multi-Criteria Chinese Word Segmentation with BERT","date":"2020-04-13","arxiv_id":"2004.05808","n_code_links":0,"syntology":null},{"paper":"/paper/amr-parsing-via-graph-sequence-iterative","slug":"amr-parsing-via-graph-sequence-iterative","title":"AMR Parsing via Graph-Sequence Iterative Inference","date":"2020-04-12","arxiv_id":"2004.05572","n_code_links":3,"syntology":{"ran":21,"of":31,"n_ran_checked":16,"n_instrument":5,"unverified":10,"pointer_only":1,"phrase":"21 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":{"repos":["jcyk/AMR-gs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"pre-training-text-representations-as-meta","title":"Pre-training Text Representations as Meta Learning","date":"2020-04-12","arxiv_id":"2004.05568","n_code_links":0,"syntology":null},{"paper":"/paper/vgcn-bert-augmenting-bert-with-graph","slug":"vgcn-bert-augmenting-bert-with-graph","title":"VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification","date":"2020-04-12","arxiv_id":"2004.05707","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Louis-udm/VGCN-BERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"end-to-end-chinese-lexical-fusion-recognition","title":"End to End Chinese Lexical Fusion Recognition with Sememe Knowledge","date":"2020-04-11","arxiv_id":"2004.05456","n_code_links":0,"syntology":null},{"paper":"/paper/lareqa-language-agnostic-answer-retrieval","slug":"lareqa-language-agnostic-answer-retrieval","title":"LAReQA: Language-agnostic answer retrieval from a multilingual pool","date":"2020-04-11","arxiv_id":"2004.05484","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-in-depth-walkthrough-on-evolution-of","title":"An In-depth Walkthrough on Evolution of Neural Machine Translation","date":"2020-04-10","arxiv_id":"2004.04902","n_code_links":0,"syntology":null},{"paper":"/paper/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","n_code_links":22,"syntology":{"ran":22,"of":35,"n_ran_checked":14,"n_instrument":8,"unverified":13,"pointer_only":5,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"simpletran-transferring-pre-trained-sentence","title":"Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer","date":"2020-04-10","arxiv_id":"2004.05119","n_code_links":0,"syntology":null},{"paper":null,"slug":"telling-bert-s-full-story-from-local","title":"Telling BERT's full story: from Local Attention to Global Aggregation","date":"2020-04-10","arxiv_id":"2004.05916","n_code_links":0,"syntology":null},{"paper":"/paper/bleurt-learning-robust-metrics-for-text","slug":"bleurt-learning-robust-metrics-for-text","title":"BLEURT: Learning Robust Metrics for Text Generation","date":"2020-04-09","arxiv_id":"2004.04696","n_code_links":4,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["google-research/bleurt"],"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":"interpretability-analysis-for-named-entity","title":"Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve","date":"2020-04-09","arxiv_id":"2004.04564","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-language-neutrality-of-pre-trained","slug":"on-the-language-neutrality-of-pre-trained","title":"On the Language Neutrality of Pre-trained Multilingual Representations","date":"2020-04-09","arxiv_id":"2004.05160","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jlibovicky/assess-multilingual-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dialbert-a-hierarchical-pre-trained-model-for","slug":"dialbert-a-hierarchical-pre-trained-model-for","title":"DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement","date":"2020-04-08","arxiv_id":"2004.03760","n_code_links":1,"syntology":null},{"paper":"/paper/dynabert-dynamic-bert-with-adaptive-width-and","slug":"dynabert-dynamic-bert-with-adaptive-width-and","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","date":"2020-04-08","arxiv_id":"2004.04037","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"error-correction-and-extraction-in-request","title":"Error correction and extraction in request dialogs","date":"2020-04-08","arxiv_id":"2004.04243","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-redundancy-in-pre-trained-language","slug":"exploiting-redundancy-in-pre-trained-language","title":"Analyzing Redundancy in Pretrained Transformer Models","date":"2020-04-08","arxiv_id":"2004.04010","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-counter-narratives-against-online","title":"Generating Counter Narratives against Online Hate Speech: Data and Strategies","date":"2020-04-08","arxiv_id":"2004.04216","n_code_links":0,"syntology":null},{"paper":"/paper/have-your-text-and-use-it-too-end-to-end","slug":"have-your-text-and-use-it-too-end-to-end","title":"Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity","date":"2020-04-08","arxiv_id":"2004.06577","n_code_links":1,"syntology":null},{"paper":"/paper/improving-bert-with-self-supervised-attention","slug":"improving-bert-with-self-supervised-attention","title":"Improving BERT with Self-Supervised Attention","date":"2020-04-08","arxiv_id":"2004.03808","n_code_links":1,"syntology":null},{"paper":null,"slug":"ladabert-lightweight-adaptation-of-bert","title":"LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression","date":"2020-04-08","arxiv_id":"2004.04124","n_code_links":0,"syntology":null},{"paper":"/paper/poor-man-s-bert-smaller-and-faster","slug":"poor-man-s-bert-smaller-and-faster","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","date":"2020-04-08","arxiv_id":"2004.03844","n_code_links":4,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"7 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hsajjad/transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/pre-training-is-a-hot-topic-contextualized","slug":"pre-training-is-a-hot-topic-contextualized","title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence","date":"2020-04-08","arxiv_id":"2004.03974","n_code_links":3,"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":["MilaNLProc/contextualized-topic-models"],"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/sciwing-a-software-toolkit-for-scientific","slug":"sciwing-a-software-toolkit-for-scientific","title":"SciWING -- A Software Toolkit for Scientific Document Processing","date":"2020-04-08","arxiv_id":"2004.03807","n_code_links":1,"syntology":null},{"paper":null,"slug":"severing-the-edge-between-before-and-after","title":"Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events","date":"2020-04-08","arxiv_id":"2004.04295","n_code_links":0,"syntology":null},{"paper":"/paper/are-natural-language-inference-models","slug":"are-natural-language-inference-models","title":"Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition","date":"2020-04-07","arxiv_id":"2004.03066","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["alexwarstadt/data_generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/evaluating-machines-by-their-real-world","slug":"evaluating-machines-by-their-real-world","title":"TuringAdvice: A Generative and Dynamic Evaluation of Language Use","date":"2020-04-07","arxiv_id":"2004.03607","n_code_links":1,"syntology":null},{"paper":"/paper/information-theoretic-probing-for-linguistic","slug":"information-theoretic-probing-for-linguistic","title":"Information-Theoretic Probing for Linguistic Structure","date":"2020-04-07","arxiv_id":"2004.03061","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["rycolab/info-theoretic-probing"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ryansql-recursively-applying-sketch-based","slug":"ryansql-recursively-applying-sketch-based","title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","date":"2020-04-07","arxiv_id":"2004.03125","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":["kakaoenterprise/RYANSQL"],"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/speaker-aware-bert-for-multi-turn-response","slug":"speaker-aware-bert-for-multi-turn-response","title":"Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots","date":"2020-04-07","arxiv_id":"2004.03588","n_code_links":2,"syntology":null},{"paper":null,"slug":"textgail-generative-adversarial-imitation","title":"TextGAIL: Generative Adversarial Imitation Learning for Text Generation","date":"2020-04-07","arxiv_id":"2004.13796","n_code_links":0,"syntology":null},{"paper":"/paper/the-russian-drug-reaction-corpus-and-neural","slug":"the-russian-drug-reaction-corpus-and-neural","title":"The Russian Drug Reaction Corpus and Neural Models for Drug Reactions and Effectiveness Detection in User Reviews","date":"2020-04-07","arxiv_id":"2004.03659","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-evaluating-the-robustness-of-chinese","title":"Towards Evaluating the Robustness of Chinese BERT Classifiers","date":"2020-04-07","arxiv_id":"2004.03742","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-task-specific-distillation-of","title":"Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation","date":"2020-04-07","arxiv_id":"2004.03097","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-to-learn-hierarchical-contexts","slug":"transformers-to-learn-hierarchical-contexts","title":"Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering","date":"2020-04-07","arxiv_id":"2004.03561","n_code_links":1,"syntology":null},{"paper":"/paper/bootstrapping-a-crosslingual-semantic-parser","slug":"bootstrapping-a-crosslingual-semantic-parser","title":"Bootstrapping a Crosslingual Semantic Parser","date":"2020-04-06","arxiv_id":"2004.02585","n_code_links":1,"syntology":null},{"paper":null,"slug":"dare-data-augmented-relation-extraction-with","title":"DARE: Data Augmented Relation Extraction with GPT-2","date":"2020-04-06","arxiv_id":"2004.13845","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-review-comprehension-with-domain","title":"Enhancing Review Comprehension with Domain-Specific Commonsense","date":"2020-04-06","arxiv_id":"2004.03020","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-the-inherent-hierarchy-of-vacancy","title":"Leveraging the Inherent Hierarchy of Vacancy Titles for Automated Job Ontology Expansion","date":"2020-04-06","arxiv_id":"2004.02814","n_code_links":0,"syntology":null},{"paper":"/paper/mobilebert-a-compact-task-agnostic-bert-for","slug":"mobilebert-a-compact-task-agnostic-bert-for","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","date":"2020-04-06","arxiv_id":"2004.02984","n_code_links":7,"syntology":null},{"paper":"/paper/sparse-text-generation","slug":"sparse-text-generation","title":"Sparse Text Generation","date":"2020-04-06","arxiv_id":"2004.02644","n_code_links":1,"syntology":null},{"paper":"/paper/fastbert-a-self-distilling-bert-with-adaptive","slug":"fastbert-a-self-distilling-bert-with-adaptive","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","date":"2020-04-05","arxiv_id":"2004.02178","n_code_links":3,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"6 ran (of which 4 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) · 5 unverified","official":{"repos":["autoliuweijie/FastBERT"],"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":"improved-pretraining-for-domain-specific","title":"Continual Domain-Tuning for Pretrained Language Models","date":"2020-04-05","arxiv_id":"2004.02288","n_code_links":0,"syntology":null},{"paper":"/paper/optimus-organizing-sentences-via-pre-trained","slug":"optimus-organizing-sentences-via-pre-trained","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","date":"2020-04-05","arxiv_id":"2004.04092","n_code_links":1,"syntology":null},{"paper":"/paper/a-dependency-syntactic-knowledge-augmented","slug":"a-dependency-syntactic-knowledge-augmented","title":"A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis","date":"2020-04-04","arxiv_id":"2004.01951","n_code_links":3,"syntology":null},{"paper":null,"slug":"cg-bert-conditional-text-generation-with-bert","title":"CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection","date":"2020-04-04","arxiv_id":"2004.01881","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-rationales-in-visual-question","title":"Generating Rationales in Visual Question Answering","date":"2020-04-04","arxiv_id":"2004.02032","n_code_links":0,"syntology":null},{"paper":"/paper/keyphrase-rubric-relationship-classification","slug":"keyphrase-rubric-relationship-classification","title":"Finding Black Cat in a Coal Cellar -- Keyphrase Extraction & Keyphrase-Rubric Relationship Classification from Complex Assignments","date":"2020-04-03","arxiv_id":"2004.01549","n_code_links":2,"syntology":null},{"paper":null,"slug":"testing-pre-trained-transformer-models-for","title":"Testing pre-trained Transformer models for Lithuanian news clustering","date":"2020-04-03","arxiv_id":"2004.03461","n_code_links":0,"syntology":null},{"paper":"/paper/xglue-a-new-benchmark-dataset-for-cross","slug":"xglue-a-new-benchmark-dataset-for-cross","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","date":"2020-04-03","arxiv_id":"2004.01401","n_code_links":2,"syntology":null},{"paper":null,"slug":"gestalt-a-stacking-ensemble-for-squad2-0","title":"Gestalt: a Stacking Ensemble for SQuAD2.0","date":"2020-04-02","arxiv_id":"2004.07067","n_code_links":0,"syntology":null},{"paper":"/paper/deep-entity-matching-with-pre-trained","slug":"deep-entity-matching-with-pre-trained","title":"Deep Entity Matching with Pre-Trained Language Models","date":"2020-04-01","arxiv_id":"2004.00584","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":["megagonlabs/ditto"],"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/give-your-text-representation-models-some","slug":"give-your-text-representation-models-some","title":"Give your Text Representation Models some Love: the Case for Basque","date":"2020-03-31","arxiv_id":"2004.00033","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-productionizing-subjective-search","title":"Towards Productionizing Subjective Search Systems","date":"2020-03-31","arxiv_id":"2003.13968","n_code_links":0,"syntology":null},{"paper":"/paper/unification-based-reconstruction-of","slug":"unification-based-reconstruction-of","title":"Unification-based Reconstruction of Multi-hop Explanations for Science Questions","date":"2020-03-31","arxiv_id":"2004.00061","n_code_links":1,"syntology":null},{"paper":"/paper/interbert-vision-and-language-interaction-for","slug":"interbert-vision-and-language-interaction-for","title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","date":"2020-03-30","arxiv_id":"2003.13198","n_code_links":0,"syntology":null},{"paper":"/paper/nukebert-a-pre-trained-language-model-for-low","slug":"nukebert-a-pre-trained-language-model-for-low","title":"NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain","date":"2020-03-30","arxiv_id":"2003.13821","n_code_links":1,"syntology":null},{"paper":"/paper/abstractive-text-summarization-based-on","slug":"abstractive-text-summarization-based-on","title":"Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling","date":"2020-03-29","arxiv_id":"2003.13027","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["axenov/BERT-Summ-OpenNMT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert-fine-tuning-for-arabic-text","slug":"bert-fine-tuning-for-arabic-text","title":"BERT Fine-tuning For Arabic Text Summarization","date":"2020-03-29","arxiv_id":"2004.14135","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":5,"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) · 0 unverified","official":{"repos":["mukhtar-algezoli/Arabic_PreSumm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-fine-tuning-neural-language-models-for","slug":"meta-fine-tuning-neural-language-models-for","title":"Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining","date":"2020-03-29","arxiv_id":"2003.13003","n_code_links":2,"syntology":null},{"paper":"/paper/recursive-non-autoregressive-graph-to-graph","slug":"recursive-non-autoregressive-graph-to-graph","title":"Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement","date":"2020-03-29","arxiv_id":"2003.13118","n_code_links":1,"syntology":null},{"paper":null,"slug":"user-generated-data-achilles-heel-of-bert","title":"Noisy Text Data: Achilles' Heel of BERT","date":"2020-03-29","arxiv_id":"2003.12932","n_code_links":0,"syntology":null},{"paper":"/paper/hin-hierarchical-inference-network-for","slug":"hin-hierarchical-inference-network-for","title":"HIN: Hierarchical Inference Network for Document-Level Relation Extraction","date":"2020-03-28","arxiv_id":"2003.12754","n_code_links":0,"syntology":null},{"paper":"/paper/cycle-text-to-image-gan-with-bert","slug":"cycle-text-to-image-gan-with-bert","title":"Cycle Text-To-Image GAN with BERT","date":"2020-03-26","arxiv_id":"2003.12137","n_code_links":4,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","n_code_links":19,"syntology":{"ran":31,"of":40,"n_ran_checked":18,"n_instrument":13,"unverified":9,"pointer_only":10,"phrase":"31 ran (of which 7 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 2 violated, 14 with no contract checked; 13 where Syntology's instrument failed) · 9 unverified","official":{"repos":["google-research/electra"],"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":["listed","unlocated"]}}},{"paper":"/paper/pairwise-multi-class-document-classification","slug":"pairwise-multi-class-document-classification","title":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","date":"2020-03-22","arxiv_id":"2003.09881","n_code_links":4,"syntology":null},{"paper":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","n_code_links":3,"syntology":null},{"paper":null,"slug":"diversity-density-and-homogeneity","title":"Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections","date":"2020-03-19","arxiv_id":"2003.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-embeddings-and-transformer-models","title":"Temporal Embeddings and Transformer Models for Narrative Text Understanding","date":"2020-03-19","arxiv_id":"2003.08811","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-value-of-text-for-small-business-default","title":"The value of text for small business default prediction: A deep learning approach","date":"2020-03-19","arxiv_id":"2003.08964","n_code_links":0,"syntology":null},{"paper":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","n_code_links":0,"syntology":null},{"paper":"/paper/x-stance-a-multilingual-multi-target-dataset","slug":"x-stance-a-multilingual-multi-target-dataset","title":"X-Stance: A Multilingual Multi-Target Dataset for Stance Detection","date":"2020-03-18","arxiv_id":"2003.08385","n_code_links":1,"syntology":null},{"paper":null,"slug":"author2vec-a-framework-for-generating-user","title":"Author2Vec: A Framework for Generating User Embedding","date":"2020-03-17","arxiv_id":"2003.11627","n_code_links":0,"syntology":null},{"paper":"/paper/calibration-of-pre-trained-transformers","slug":"calibration-of-pre-trained-transformers","title":"Calibration of Pre-trained Transformers","date":"2020-03-17","arxiv_id":"2003.07892","n_code_links":1,"syntology":null},{"paper":"/paper/po-emo-conceptualization-annotation-and","slug":"po-emo-conceptualization-annotation-and","title":"PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry","date":"2020-03-17","arxiv_id":"2003.07723","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-contextual-embeddings","title":"A Survey on Contextual Embeddings","date":"2020-03-16","arxiv_id":"2003.07278","n_code_links":0,"syntology":null},{"paper":"/paper/cost-sensitive-bert-for-generalisable-1","slug":"cost-sensitive-bert-for-generalisable-1","title":"Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data","date":"2020-03-16","arxiv_id":"2003.11563","n_code_links":1,"syntology":null},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","slug":"trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","arxiv_id":"2003.07000","n_code_links":0,"syntology":null},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","slug":"document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","n_code_links":2,"syntology":null},{"paper":null,"slug":"finnish-language-modeling-with-deep","title":"Finnish Language Modeling with Deep Transformer Models","date":"2020-03-14","arxiv_id":"2003.11562","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-major-types-of-chinese-classical","title":"Generating Major Types of Chinese Classical Poetry in a Uniformed Framework","date":"2020-03-13","arxiv_id":"2003.11528","n_code_links":0,"syntology":null},{"paper":"/paper/hurtful-words-quantifying-biases-in-clinical","slug":"hurtful-words-quantifying-biases-in-clinical","title":"Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings","date":"2020-03-11","arxiv_id":"2003.11515","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-entity-knowledge-in-bert-with-1","slug":"investigating-entity-knowledge-in-bert-with-1","title":"Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking","date":"2020-03-11","arxiv_id":"2003.05473","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":["samuelbroscheit/entity_knowledge_in_bert"],"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/keyword-attentive-deep-semantic-matching","slug":"keyword-attentive-deep-semantic-matching","title":"Keyword-Attentive Deep Semantic Matching","date":"2020-03-11","arxiv_id":"2003.11516","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-intent-detection-with-dual-sentence","slug":"efficient-intent-detection-with-dual-sentence","title":"Efficient Intent Detection with Dual Sentence Encoders","date":"2020-03-10","arxiv_id":"2003.04807","n_code_links":5,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":null,"slug":"sensitive-data-detection-and-classification","title":"Sensitive Data Detection and Classification in Spanish Clinical Text: Experiments with BERT","date":"2020-03-06","arxiv_id":"2003.03106","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-for-information-extraction","title":"Transfer Learning for Information Extraction with Limited Data","date":"2020-03-06","arxiv_id":"2003.03064","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-as-a-teacher-contextual-embeddings-for","title":"BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward","date":"2020-03-05","arxiv_id":"2003.02738","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyponli-exploring-the-artificial-patterns-of","title":"HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference","date":"2020-03-05","arxiv_id":"2003.02756","n_code_links":0,"syntology":null},{"paper":"/paper/recipegpt-generative-pre-training-based","slug":"recipegpt-generative-pre-training-based","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","date":"2020-03-05","arxiv_id":"2003.02498","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-the-mask-making-sense-of-language","title":"What the [MASK]? Making Sense of Language-Specific BERT Models","date":"2020-03-05","arxiv_id":"2003.02912","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-efficiency-accuracy-and-document","title":"A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection","date":"2020-03-04","arxiv_id":"2003.02349","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-using-pre-trained","slug":"data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","date":"2020-03-04","arxiv_id":"2003.02245","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["varinf/TransformersDataAugmentation"],"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/jiant-a-software-toolkit-for-research-on","slug":"jiant-a-software-toolkit-for-research-on","title":"jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models","date":"2020-03-04","arxiv_id":"2003.02249","n_code_links":6,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 3 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) · 2 unverified","official":{"repos":["nyu-mll/jiant"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kleister-a-novel-task-for-information","title":"Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout","date":"2020-03-04","arxiv_id":"2003.02356","n_code_links":0,"syntology":null}],"record_sha256":"2c5ae5897514b4692b704ca0092f5a80de7e30217637bde47b035f09dcaee937","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}