{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-warmup-with-linear-decay/papers/66","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear Decay","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":66,"pages_in_order":71,"rows_per_page":100,"rows":[6501,6600],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/65","next":"/method/linear-warmup-with-linear-decay/papers/67","papers":[{"paper":null,"slug":"the-performance-evaluation-of-multi","title":"The performance evaluation of Multi-representation in the Deep Learning models for Relation Extraction Task","date":"2019-12-17","arxiv_id":"1912.08290","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-malware-representation-based-on","title":"Learning Malware Representation based on Execution Sequences","date":"2019-12-16","arxiv_id":"1912.07250","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-is-not-enough-bert-for-finnish","slug":"multilingual-is-not-enough-bert-for-finnish","title":"Multilingual is not enough: BERT for Finnish","date":"2019-12-15","arxiv_id":"1912.07076","n_code_links":1,"syntology":null},{"paper":"/paper/robust-named-entity-recognition-with","slug":"robust-named-entity-recognition-with","title":"Robust Named Entity Recognition with Truecasing Pretraining","date":"2019-12-15","arxiv_id":"1912.07095","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertqa-attention-on-steroids","title":"BERTQA -- Attention on Steroids","date":"2019-12-14","arxiv_id":"1912.10435","n_code_links":0,"syntology":null},{"paper":"/paper/towards-robust-toxic-content-classification","slug":"towards-robust-toxic-content-classification","title":"Towards Robust Toxic Content Classification","date":"2019-12-14","arxiv_id":"1912.06872","n_code_links":1,"syntology":null},{"paper":"/paper/topoact-exploring-the-shape-of-activations-in","slug":"topoact-exploring-the-shape-of-activations-in","title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","date":"2019-12-13","arxiv_id":"1912.06332","n_code_links":1,"syntology":null},{"paper":null,"slug":"waldorf-wasteless-language-model-distillation","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","date":"2019-12-13","arxiv_id":"1912.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-has-a-moral-compass-improvements-of","title":"BERT has a Moral Compass: Improvements of ethical and moral values of machines","date":"2019-12-11","arxiv_id":"1912.05238","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-transfer-learning-via-bert","title":"Unsupervised Transfer Learning via BERT Neuron Selection","date":"2019-12-10","arxiv_id":"1912.05308","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-analysis-of-natural-language","title":"Adversarial Analysis of Natural Language Inference Systems","date":"2019-12-07","arxiv_id":"1912.03441","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-patent-claim-generation-and","title":"Personalized Patent Claim Generation and Measurement","date":"2019-12-07","arxiv_id":"1912.03502","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-adam-beats-sgd-for-attention-models-1","title":"Why are Adaptive Methods Good for Attention Models?","date":"2019-12-06","arxiv_id":"1912.03194","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-contextual-language","title":"Self-Supervised Contextual Language Representation of Radiology Reports to Improve the Identification of Communication Urgency","date":"2019-12-05","arxiv_id":"1912.02703","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-knowledge-from-pre-trained-model-to","title":"Acquiring Knowledge from Pre-trained Model to Neural Machine Translation","date":"2019-12-04","arxiv_id":"1912.01774","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-data-augmentation-and-1","title":"An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering","date":"2019-12-04","arxiv_id":"1912.02145","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-relation-extraction-using-syntactic","slug":"enhancing-relation-extraction-using-syntactic","title":"Enhancing Relation Extraction Using Syntactic Indicators and Sentential Contexts","date":"2019-12-04","arxiv_id":"1912.01858","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pretrained-language","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","date":"2019-12-03","arxiv_id":"1912.01580","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-large-scale-video-segment","title":"BERT for Large-scale Video Segment Classification with Test-time Augmentation","date":"2019-12-02","arxiv_id":"1912.01127","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-contextual-embeddings-for","title":"Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift","date":"2019-12-02","arxiv_id":"1912.01072","n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-accurate-stochastic-gradient","slug":"fast-and-accurate-stochastic-gradient","title":"Fast and Accurate Stochastic Gradient Estimation","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-relational-knowledge-from-bert","title":"Inducing Relational Knowledge from BERT","date":"2019-11-28","arxiv_id":"1911.12753","n_code_links":0,"syntology":null},{"paper":"/paper/do-attention-heads-in-bert-track-syntactic","slug":"do-attention-heads-in-bert-track-syntactic","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","date":"2019-11-27","arxiv_id":"1911.12246","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":null,"slug":"taking-a-stance-on-fake-news-towards","title":"Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection","date":"2019-11-27","arxiv_id":"1911.11951","n_code_links":0,"syntology":null},{"paper":"/paper/low-rank-factorization-for-compact-multi-head","slug":"low-rank-factorization-for-compact-multi-head","title":"Low Rank Factorization for Compact Multi-Head Self-Attention","date":"2019-11-26","arxiv_id":"1912.00835","n_code_links":1,"syntology":null},{"paper":"/paper/who-did-they-respond-to-conversation","slug":"who-did-they-respond-to-conversation","title":"Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer","date":"2019-11-25","arxiv_id":"1911.10666","n_code_links":1,"syntology":null},{"paper":"/paper/automatically-neutralizing-subjective-bias-in","slug":"automatically-neutralizing-subjective-bias-in","title":"Automatically Neutralizing Subjective Bias in Text","date":"2019-11-21","arxiv_id":"1911.09709","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rpryzant/neutralizing-bias"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/chemical-protein-interaction-extraction-via","slug":"chemical-protein-interaction-extraction-via","title":"Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge","date":"2019-11-21","arxiv_id":"1911.09487","n_code_links":1,"syntology":null},{"paper":null,"slug":"joint-emotion-label-space-modelling-for","title":"Joint Emotion Label Space Modelling for Affect Lexica","date":"2019-11-20","arxiv_id":"1911.08782","n_code_links":0,"syntology":null},{"paper":"/paper/towards-lingua-franca-named-entity","slug":"towards-lingua-franca-named-entity","title":"Towards Lingua Franca Named Entity Recognition with BERT","date":"2019-11-19","arxiv_id":"1912.01389","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-toxic-landscapes-automatic-toxic","title":"Towards non-toxic landscapes: Automatic toxic comment detection using DNN","date":"2019-11-19","arxiv_id":"1911.08395","n_code_links":0,"syntology":null},{"paper":"/paper/improving-relation-classification-by-entity","slug":"improving-relation-classification-by-entity","title":"Improving Relation Classification by Entity Pair Graph","date":"2019-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-visual-representation-learning-2","title":"Unsupervised Visual Representation Learning with Increasing Object Shape Bias","date":"2019-11-17","arxiv_id":"1911.07272","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-reading-comprehension-with-linguistic","title":"Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization","date":"2019-11-16","arxiv_id":"1911.06948","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robustness-of-language-models-for","title":"Evaluating robustness of language models for chief complaint extraction from patient-generated text","date":"2019-11-15","arxiv_id":"1911.06915","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-and-evaluating-a-deep-learning","title":"Adapting and evaluating a deep learning language model for clinical why-question answering","date":"2019-11-13","arxiv_id":"1911.05604","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-domain-adaptation-on-reading","slug":"unsupervised-domain-adaptation-on-reading","title":"Unsupervised Domain Adaptation on Reading Comprehension","date":"2019-11-13","arxiv_id":"1911.06137","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-do-you-mean-bert-assessing-bert-as-a","title":"What do you mean, BERT? Assessing BERT as a Distributional Semantics Model","date":"2019-11-13","arxiv_id":"1911.05758","n_code_links":0,"syntology":null},{"paper":"/paper/a-syntax-aware-multi-task-learning-framework-1","slug":"a-syntax-aware-multi-task-learning-framework-1","title":"A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling","date":"2019-11-12","arxiv_id":"1911.04641","n_code_links":1,"syntology":null},{"paper":null,"slug":"attending-to-entities-for-better-text","title":"Attending to Entities for Better Text Understanding","date":"2019-11-11","arxiv_id":"1911.04361","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-answering-for-machine-reading","title":"Meta Answering for Machine Reading","date":"2019-11-11","arxiv_id":"1911.04156","n_code_links":0,"syntology":null},{"paper":"/paper/negbert-a-transfer-learning-approach-for","slug":"negbert-a-transfer-learning-approach-for","title":"NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolution","date":"2019-11-11","arxiv_id":"1911.04211","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-bert-performance-in-propaganda-1","title":"Understanding BERT performance in propaganda analysis","date":"2019-11-11","arxiv_id":"1911.04525","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-the-knowledge-of-bert-for-text-1","slug":"distilling-the-knowledge-of-bert-for-text-1","title":"Distilling Knowledge Learned in BERT for Text Generation","date":"2019-11-10","arxiv_id":"1911.03829","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["ChenRocks/Distill-BERT-Textgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/effectiveness-of-self-supervised-pre-training","slug":"effectiveness-of-self-supervised-pre-training","title":"Effectiveness of self-supervised pre-training for speech recognition","date":"2019-11-10","arxiv_id":"1911.03912","n_code_links":2,"syntology":null},{"paper":null,"slug":"improving-bert-fine-tuning-with-embedding","title":"Improving BERT Fine-tuning with Embedding Normalization","date":"2019-11-10","arxiv_id":"1911.03918","n_code_links":0,"syntology":null},{"paper":"/paper/inset-sentence-infilling-with-inter","slug":"inset-sentence-infilling-with-inter","title":"INSET: Sentence Infilling with INter-SEntential Transformer","date":"2019-11-10","arxiv_id":"1911.03892","n_code_links":1,"syntology":null},{"paper":"/paper/rat-sql-relation-aware-schema-encoding-and-1","slug":"rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","arxiv_id":"1911.04942","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Microsoft/rat-sql"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robust-natural-language-inference-models-with","title":"Increasing Robustness to Spurious Correlations using Forgettable Examples","date":"2019-11-10","arxiv_id":"1911.03861","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntax-infused-transformer-and-bert-models","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","date":"2019-11-10","arxiv_id":"1911.06156","n_code_links":0,"syntology":null},{"paper":null,"slug":"yelm-end-to-end-contextualized-entity-linking","title":"Contextualized End-to-End Neural Entity Linking","date":"2019-11-10","arxiv_id":"1911.03834","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-entity-linking-with-dense-entity","slug":"zero-shot-entity-linking-with-dense-entity","title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","date":"2019-11-10","arxiv_id":"1911.03814","n_code_links":3,"syntology":null},{"paper":null,"slug":"attentive-student-meets-multi-task-teacher","title":"MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models","date":"2019-11-09","arxiv_id":"1911.03588","n_code_links":0,"syntology":null},{"paper":"/paper/bert-is-not-a-knowledge-base-yet-factual","slug":"bert-is-not-a-knowledge-base-yet-factual","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","date":"2019-11-09","arxiv_id":"1911.03681","n_code_links":1,"syntology":null},{"paper":"/paper/convert-efficient-and-accurate-conversational","slug":"convert-efficient-and-accurate-conversational","title":"ConveRT: Efficient and Accurate Conversational Representations from Transformers","date":"2019-11-09","arxiv_id":"1911.03688","n_code_links":5,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"multi-perspective-inferrer-reasoning","title":"Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective","date":"2019-11-09","arxiv_id":"1911.03668","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dialogue-dodecathlon-open-domain","title":"The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents","date":"2019-11-09","arxiv_id":"1911.03768","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-relevance-transfer-for-document","title":"Cross-Lingual Relevance Transfer for Document Retrieval","date":"2019-11-08","arxiv_id":"1911.02989","n_code_links":0,"syntology":null},{"paper":"/paper/graph-to-graph-transformer-for-transition","slug":"graph-to-graph-transformer-for-transition","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","date":"2019-11-08","arxiv_id":"1911.03561","n_code_links":1,"syntology":null},{"paper":"/paper/how-language-neutral-is-multilingual-bert","slug":"how-language-neutral-is-multilingual-bert","title":"How Language-Neutral is Multilingual BERT?","date":"2019-11-08","arxiv_id":"1911.03310","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretrained-language-models-for-document-level","title":"Pretrained Language Models for Document-Level Neural Machine Translation","date":"2019-11-08","arxiv_id":"1911.03110","n_code_links":0,"syntology":null},{"paper":null,"slug":"resurrecting-submodularity-in-neural","title":"Resurrecting Submodularity for Neural Text Generation","date":"2019-11-08","arxiv_id":"1911.03014","n_code_links":0,"syntology":null},{"paper":null,"slug":"sept-improving-scientific-named-entity","title":"SEPT: Improving Scientific Named Entity Recognition with Span Representation","date":"2019-11-08","arxiv_id":"1911.03353","n_code_links":0,"syntology":null},{"paper":"/paper/towards-hierarchical-importance-attribution-1","slug":"towards-hierarchical-importance-attribution-1","title":"Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models","date":"2019-11-08","arxiv_id":"1911.06194","n_code_links":3,"syntology":null},{"paper":null,"slug":"transforming-wikipedia-into-augmented-data","title":"Transforming Wikipedia into Augmented Data for Query-Focused Summarization","date":"2019-11-08","arxiv_id":"1911.03324","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-would-elsa-do-freezing-layers-during","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","date":"2019-11-08","arxiv_id":"1911.03090","n_code_links":0,"syntology":null},{"paper":"/paper/berts-of-a-feather-do-not-generalize-together","slug":"berts-of-a-feather-do-not-generalize-together","title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","date":"2019-11-07","arxiv_id":"1911.02969","n_code_links":1,"syntology":null},{"paper":"/paper/blockwise-self-attention-for-long-document","slug":"blockwise-self-attention-for-long-document","title":"Blockwise Self-Attention for Long Document Understanding","date":"2019-11-07","arxiv_id":"1911.02972","n_code_links":1,"syntology":null},{"paper":null,"slug":"explicit-pairwise-word-interaction-modeling","title":"Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks","date":"2019-11-07","arxiv_id":"1911.02847","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-lig-system-for-the-english-czech-text","title":"The LIG system for the English-Czech Text Translation Task of IWSLT 2019","date":"2019-11-07","arxiv_id":"1911.02898","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-dynamic-embeddings-to-improve-static","title":"How Can BERT Help Lexical Semantics Tasks?","date":"2019-11-07","arxiv_id":"1911.02929","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-answer-by-learning-to-ask-getting","title":"Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds","date":"2019-11-06","arxiv_id":"1911.02365","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-domain-adaptation-of-contextual","title":"Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection","date":"2019-11-06","arxiv_id":"1911.02645","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepening-hidden-representations-from-pre","title":"Deepening Hidden Representations from Pre-trained Language Models","date":"2019-11-05","arxiv_id":"1911.01940","n_code_links":0,"syntology":null},{"paper":"/paper/improving-slot-filling-by-utilizing","slug":"improving-slot-filling-by-utilizing","title":"Improving Slot Filling by Utilizing Contextual Information","date":"2019-11-05","arxiv_id":"1911.01680","n_code_links":0,"syntology":null},{"paper":null,"slug":"incremental-sense-weight-training-for-the","title":"Incremental Sense Weight Training for the Interpretation of Contextualized Word Embeddings","date":"2019-11-05","arxiv_id":"1911.01623","n_code_links":0,"syntology":null},{"paper":"/paper/mml-maximal-multiverse-learning-for-robust","slug":"mml-maximal-multiverse-learning-for-robust","title":"MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language Models","date":"2019-11-05","arxiv_id":"1911.06182","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-cross-lingual-representation-1","slug":"unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","arxiv_id":"1911.02116","n_code_links":35,"syntology":{"ran":40,"of":59,"n_ran_checked":35,"n_instrument":5,"unverified":19,"pointer_only":52,"phrase":"40 ran (of which 13 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","official":{"repos":["facebookresearch/cc_net","facebookresearch/XLM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/assessing-social-and-intersectional-biases-in","slug":"assessing-social-and-intersectional-biases-in","title":"Assessing Social and Intersectional Biases in Contextualized Word Representations","date":"2019-11-04","arxiv_id":"1911.01485","n_code_links":1,"syntology":null},{"paper":null,"slug":"bas-an-answer-selection-method-using-bert","title":"BAS: An Answer Selection Method Using BERT Language Model","date":"2019-11-04","arxiv_id":"1911.01528","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentence-level-bert-and-multi-task-learning","title":"Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media","date":"2019-11-02","arxiv_id":"1911.00637","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-learning-based-system-for-pharmaconer","title":"A Deep Learning-Based System for PharmaCoNER","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-framework-for-2","title":"A Multi-Task Learning Framework for Extracting Bacteria Biotope Information","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-recurrent-bert-based-model-for-question","slug":"a-recurrent-bert-based-model-for-question","title":"A Recurrent BERT-based Model for Question Generation","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"aggregating-bidirectional-encoder","title":"Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-bert-to-document-retrieval-with","title":"Applying BERT to Document Retrieval with Birch","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-goes-to-law-school-quantifying-the","title":"BERT Goes to Law School: Quantifying the Competitive Advantage of Access to Large Legal Corpora in Contract Understanding","date":"2019-11-01","arxiv_id":"1911.00473","n_code_links":0,"syntology":null},{"paper":"/paper/bert-is-not-an-interlingua-and-the-bias-of","slug":"bert-is-not-an-interlingua-and-the-bias-of","title":"BERT is Not an Interlingua and the Bias of Tokenization","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/biomedical-named-entity-recognition-with","slug":"biomedical-named-entity-recognition-with","title":"Biomedical Named Entity Recognition with Multilingual BERT","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"blcu-nlp-at-coin-shared-task1-stagewise-fine","title":"BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"caunlp-at-nlp4if-2019-shared-task-context","title":"CAUnLP at NLP4IF 2019 Shared Task: Context-Dependent BERT for Sentence-Level Propaganda Detection","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cler-cross-task-learning-with-expert","title":"CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-unsupervised-pre-training-and","title":"Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-cross-lingual-event-trigger","title":"Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-sensitive-bert-for-generalisable","title":"Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-modeling-of-sentence-level","title":"Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-bidirectional-transformers-for-relation-1","title":"Deep Bidirectional Transformers for Relation Extraction without Supervision","date":"2019-11-01","arxiv_id":"1911.00313","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-propaganda-using-logistic","title":"Detection of Propaganda Using Logistic Regression","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"cc3234882ab783a15f20b16d38906562457618e36fc6ee887672384029cd5048","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}