{"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/53","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":53,"pages_in_order":71,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/method/linear-warmup-with-linear-decay/papers/54","papers":[{"paper":"/paper/bert-family-eat-word-salad-experiments-with","slug":"bert-family-eat-word-salad-experiments-with","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","date":"2021-01-10","arxiv_id":"2101.03453","n_code_links":1,"syntology":null},{"paper":"/paper/cisco-at-aaai-cad21-shared-task-predicting","slug":"cisco-at-aaai-cad21-shared-task-predicting","title":"Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings","date":"2021-01-10","arxiv_id":"2101.11422","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-sentence-representation-with","title":"Learning Better Sentence Representation with Syntax Information","date":"2021-01-09","arxiv_id":"2101.03343","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-non-local-alignment-over-full","slug":"contextual-non-local-alignment-over-full","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","date":"2021-01-08","arxiv_id":"2101.03036","n_code_links":2,"syntology":null},{"paper":null,"slug":"misspelling-correction-with-pre-trained","title":"Misspelling Correction with Pre-trained Contextual Language Model","date":"2021-01-08","arxiv_id":"2101.03204","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-transfer-learning-for-improving","title":"Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity","date":"2021-01-07","arxiv_id":"2101.02351","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-text-transformers-in-aaai-2021","slug":"exploring-text-transformers-in-aaai-2021","title":"Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English","date":"2021-01-07","arxiv_id":"2101.02359","n_code_links":1,"syntology":null},{"paper":null,"slug":"homonym-identification-using-bert-using-a","title":"Homonym Identification using BERT -- Using a Clustering Approach","date":"2021-01-07","arxiv_id":"2101.02398","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-approach-towards-music","slug":"transformer-based-approach-towards-music","title":"Transformer-based approach towards music emotion recognition from lyrics","date":"2021-01-06","arxiv_id":"2101.02051","n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-comparative-analysis-of-methods-for","title":"COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data","date":"2021-01-05","arxiv_id":"2101.02017","n_code_links":0,"syntology":null},{"paper":"/paper/i-bert-integer-only-bert-quantization","slug":"i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","date":"2021-01-05","arxiv_id":"2101.01321","n_code_links":7,"syntology":null},{"paper":"/paper/improving-reference-mining-in-patents-with","slug":"improving-reference-mining-in-patents-with","title":"Improving reference mining in patents with BERT","date":"2021-01-04","arxiv_id":"2101.01039","n_code_links":1,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","n_code_links":1,"syntology":null},{"paper":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","n_code_links":2,"syntology":null},{"paper":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","n_code_links":2,"syntology":null},{"paper":null,"slug":"lex-bert-enhancing-bert-based-ner-with","title":"Lex-BERT: Enhancing BERT based NER with lexicons","date":"2021-01-02","arxiv_id":"2101.00396","n_code_links":0,"syntology":null},{"paper":"/paper/superbizarre-is-not-superb-improving-bert-s","slug":"superbizarre-is-not-superb-improving-bert-s","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","date":"2021-01-02","arxiv_id":"2101.00403","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["valentinhofmann/superbizarre"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-all-do-audio-transformer-models-hear","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","date":"2021-01-02","arxiv_id":"2101.00387","n_code_links":0,"syntology":null},{"paper":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-tune-enhance-bert-performance-in-low","title":"Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-probe-bert-for-efficient-and-effective","title":"Cross-Probe BERT for Efficient and Effective Cross-Modal Search","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-increasing-the-efficiency-and","title":"DACT-BERT: Increasing the efficiency and interpretability of BERT by using adaptive computation time.","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-aware-low-rank-compression-for-large-nlp","title":"Data-aware Low-Rank Compression for Large NLP Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-proteins-using-a-triplet-bert","title":"Deep Learning Proteins using a Triplet-BERT network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-slot-relationship-modeling-using-a-pre","title":"Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"erasure-for-advancing-dynamic-self-supervised","title":"Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-vulnerabilities-of-bert-based-apis","title":"EXPLORING VULNERABILITIES OF BERT-BASED APIS","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropy-in-the-contextual-embedding-space","title":"Isotropy in the Contextual Embedding Space: Clusters and Manifolds","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modelling-drug-target-binding-affinity-using","title":"Modelling Drug-Target Binding Affinity using a BERT based Graph Neural network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-span-question-answering-using-span","title":"MULTI-SPAN QUESTION ANSWERING USING SPAN-IMAGE NETWORK","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-explaining-your-explanations-of-bert-an","slug":"on-explaining-your-explanations-of-bert-an","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","date":"2021-01-01","arxiv_id":"2101.00196","n_code_links":2,"syntology":null},{"paper":null,"slug":"post-training-weighted-quantization-of-neural","title":"Post-Training Weighted Quantization of Neural Networks for Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify","title":"SkillBERT: “Skilling” the BERT to classify skills!","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speeding-up-deep-learning-training-by-sharing","title":"Speeding up Deep Learning Training by Sharing Weights and Then Unsharing","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-relevance-xlnet-word-embedding","title":"Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-notes-on-the-fly-helps-language-pre","title":"Taking Notes on the Fly Helps Language Pre-Training","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"task-agnostic-and-adaptive-size-bert","title":"Task-Agnostic and Adaptive-Size BERT Compression","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-practical-second-order-optimization","slug":"towards-practical-second-order-optimization","title":"Towards Practical Second Order Optimization for Deep Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"u-bert-pre-training-user-representations-for","title":"U-BERT: Pre-training User Representations for Improved Recommendation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"userbert-self-supervised-user-representation","title":"UserBERT: Self-supervised User Representation Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-closer-look-at-few-shot-crosslingual","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","date":"2020-12-31","arxiv_id":"2012.15682","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-modal-deep-learning-model-for-video","title":"A Multi-modal Deep Learning Model for Video Thumbnail Selection","date":"2020-12-31","arxiv_id":"2101.00073","n_code_links":0,"syntology":null},{"paper":"/paper/better-robustness-by-more-coverage","slug":"better-robustness-by-more-coverage","title":"Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning","date":"2020-12-31","arxiv_id":"2012.15699","n_code_links":1,"syntology":null},{"paper":"/paper/binarybert-pushing-the-limit-of-bert","slug":"binarybert-pushing-the-limit-of-bert","title":"BinaryBERT: Pushing the Limit of BERT Quantization","date":"2020-12-31","arxiv_id":"2012.15701","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"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":["huawei-noah/Pretrained-Language-Model"],"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","unlocated"]}}},{"paper":"/paper/cocolm-complex-commonsense-enhanced-language","slug":"cocolm-complex-commonsense-enhanced-language","title":"CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations","date":"2020-12-31","arxiv_id":"2012.15643","n_code_links":1,"syntology":null},{"paper":"/paper/earlybert-efficient-bert-training-via-early-1","slug":"earlybert-efficient-bert-training-via-early-1","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","date":"2020-12-31","arxiv_id":"2101.00063","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["VITA-Group/EarlyBERT"],"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","unlocated"]}}},{"paper":"/paper/kart-privacy-leakage-framework-of-language","slug":"kart-privacy-leakage-framework-of-language","title":"KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models","date":"2020-12-31","arxiv_id":"2101.00036","n_code_links":1,"syntology":null},{"paper":"/paper/linear-time-wordpiece-tokenization","slug":"linear-time-wordpiece-tokenization","title":"Fast WordPiece Tokenization","date":"2020-12-31","arxiv_id":"2012.15524","n_code_links":1,"syntology":null},{"paper":"/paper/minilmv2-multi-head-self-attention-relation","slug":"minilmv2-multi-head-self-attention-relation","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","date":"2020-12-31","arxiv_id":"2012.15828","n_code_links":2,"syntology":null},{"paper":"/paper/unified-mandarin-tts-front-end-based-on","slug":"unified-mandarin-tts-front-end-based-on","title":"Unified Mandarin TTS Front-end Based on Distilled BERT Model","date":"2020-12-31","arxiv_id":"2012.15404","n_code_links":1,"syntology":null},{"paper":"/paper/unks-everywhere-adapting-multilingual","slug":"unks-everywhere-adapting-multilingual","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","date":"2020-12-31","arxiv_id":"2012.15562","n_code_links":2,"syntology":null},{"paper":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","n_code_links":2,"syntology":null},{"paper":null,"slug":"deriving-contextualised-semantic-features","title":"Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings","date":"2020-12-30","arxiv_id":"2012.15353","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-with-syntax-aware-local","slug":"improving-bert-with-syntax-aware-local","title":"Improving BERT with Syntax-aware Local Attention","date":"2020-12-30","arxiv_id":"2012.15150","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-deeper-transformers-on-small","slug":"optimizing-deeper-transformers-on-small","title":"Optimizing Deeper Transformers on Small Datasets","date":"2020-12-30","arxiv_id":"2012.15355","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-order-how-important-is-the-sequential","title":"Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?","date":"2020-12-30","arxiv_id":"2012.15180","n_code_links":0,"syntology":null},{"paper":"/paper/semglove-semantic-co-occurrences-for-glove","slug":"semglove-semantic-co-occurrences-for-glove","title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT","date":"2020-12-30","arxiv_id":"2012.15197","n_code_links":3,"syntology":null},{"paper":"/paper/unnatural-language-inference","slug":"unnatural-language-inference","title":"UnNatural Language Inference","date":"2020-12-30","arxiv_id":"2101.00010","n_code_links":1,"syntology":null},{"paper":"/paper/a-paragraph-level-multi-task-learning-model","slug":"a-paragraph-level-multi-task-learning-model","title":"A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification","date":"2020-12-28","arxiv_id":"2012.14500","n_code_links":1,"syntology":null},{"paper":null,"slug":"burt-bert-inspired-universal-representation-1","title":"BURT: BERT-inspired Universal Representation from Learning Meaningful Segment","date":"2020-12-28","arxiv_id":"2012.14320","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-enhanced-pre-trained-model","slug":"syntax-enhanced-pre-trained-model","title":"Syntax-Enhanced Pre-trained Model","date":"2020-12-28","arxiv_id":"2012.14116","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-network-using-shared","title":"A multi-task learning network using shared BERT models for aspect-based sentiment analysis","date":"2020-12-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alp-kd-attention-based-layer-projection-for","title":"ALP-KD: Attention-Based Layer Projection for Knowledge Distillation","date":"2020-12-27","arxiv_id":"2012.14022","n_code_links":0,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-model-for-dialogue","slug":"an-embarrassingly-simple-model-for-dialogue","title":"An Embarrassingly Simple Model for Dialogue Relation Extraction","date":"2020-12-27","arxiv_id":"2012.13873","n_code_links":1,"syntology":null},{"paper":"/paper/inserting-information-bottlenecks-for","slug":"inserting-information-bottlenecks-for","title":"Inserting Information Bottlenecks for Attribution in Transformers","date":"2020-12-27","arxiv_id":"2012.13838","n_code_links":1,"syntology":null},{"paper":"/paper/medal-medical-abbreviation-disambiguation","slug":"medal-medical-abbreviation-disambiguation","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","date":"2020-12-27","arxiv_id":"2012.13978","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-based-model-agnostic-nlp","slug":"sentence-based-model-agnostic-nlp","title":"On the Granularity of Explanations in Model Agnostic NLP Interpretability","date":"2020-12-24","arxiv_id":"2012.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"to-what-extent-do-human-explanations-of-model","title":"To what extent do human explanations of model behavior align with actual model behavior?","date":"2020-12-24","arxiv_id":"2012.13354","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","n_code_links":2,"syntology":null},{"paper":"/paper/detecting-hate-speech-in-memes-using","slug":"detecting-hate-speech-in-memes-using","title":"Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge","date":"2020-12-23","arxiv_id":"2012.12975","n_code_links":1,"syntology":null},{"paper":null,"slug":"applying-wav2vec2-0-to-speech-recognition-in","title":"Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages","date":"2020-12-22","arxiv_id":"2012.12121","n_code_links":0,"syntology":null},{"paper":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","n_code_links":1,"syntology":null},{"paper":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","n_code_links":2,"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":["rabeehk/compacter"],"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/learning-to-retrieve-entity-aware-knowledge","slug":"learning-to-retrieve-entity-aware-knowledge","title":"Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems","date":"2020-12-22","arxiv_id":"2012.11937","n_code_links":1,"syntology":null},{"paper":"/paper/recognizing-emotion-cause-in-conversations-1","slug":"recognizing-emotion-cause-in-conversations-1","title":"Recognizing Emotion Cause in Conversations","date":"2020-12-22","arxiv_id":"2012.11820","n_code_links":1,"syntology":null},{"paper":"/paper/cross-domain-retrieval-in-the-legal-and","slug":"cross-domain-retrieval-in-the-legal-and","title":"Cross-domain Retrieval in the Legal and Patent Domains: a Reproducibility Study","date":"2020-12-21","arxiv_id":"2012.11405","n_code_links":1,"syntology":null},{"paper":"/paper/domain-specific-bert-representation-for-named","slug":"domain-specific-bert-representation-for-named","title":"Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-12-21","arxiv_id":"2012.11145","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-parsbert-and-pretrained-mt5-for","slug":"leveraging-parsbert-and-pretrained-mt5-for","title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","date":"2020-12-21","arxiv_id":"2012.11204","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-incorporating-entity-specific","title":"Towards Incorporating Entity-specific Knowledge Graph Information in Predicting Drug-Drug Interactions","date":"2020-12-21","arxiv_id":"2012.11142","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-using-pre-trained-bert","slug":"an-empirical-study-of-using-pre-trained-bert","title":"An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020","date":"2020-12-18","arxiv_id":"2012.10275","n_code_links":1,"syntology":null},{"paper":"/paper/hatexplain-a-benchmark-dataset-for","slug":"hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","arxiv_id":"2012.10289","n_code_links":6,"syntology":null},{"paper":"/paper/on-modality-bias-in-the-tvqa-dataset","slug":"on-modality-bias-in-the-tvqa-dataset","title":"On Modality Bias in the TVQA Dataset","date":"2020-12-18","arxiv_id":"2012.10210","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-white-box-analysis-of-colbert","title":"A White Box Analysis of ColBERT","date":"2020-12-17","arxiv_id":"2012.09650","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-shopping-comparing-distributional","slug":"bert-goes-shopping-comparing-distributional","title":"BERT Goes Shopping: Comparing Distributional Models for Product Representations","date":"2020-12-17","arxiv_id":"2012.09807","n_code_links":1,"syntology":null},{"paper":"/paper/literature-retrieval-for-precision-medicine","slug":"literature-retrieval-for-precision-medicine","title":"Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization","date":"2020-12-17","arxiv_id":"2012.09355","n_code_links":1,"syntology":null},{"paper":"/paper/masker-masked-keyword-regularization-for","slug":"masker-masked-keyword-regularization-for","title":"MASKER: Masked Keyword Regularization for Reliable Text Classification","date":"2020-12-17","arxiv_id":"2012.09392","n_code_links":1,"syntology":null},{"paper":null,"slug":"mix-a-multi-task-learning-approach-to-solve","title":"MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering","date":"2020-12-17","arxiv_id":"2012.09766","n_code_links":0,"syntology":null},{"paper":"/paper/sceneformer-indoor-scene-generation-with","slug":"sceneformer-indoor-scene-generation-with","title":"SceneFormer: Indoor Scene Generation with Transformers","date":"2020-12-17","arxiv_id":"2012.09793","n_code_links":2,"syntology":null},{"paper":"/paper/a-lightweight-neural-model-for-biomedical","slug":"a-lightweight-neural-model-for-biomedical","title":"A Lightweight Neural Model for Biomedical Entity Linking","date":"2020-12-16","arxiv_id":"2012.08844","n_code_links":1,"syntology":null},{"paper":"/paper/dialogxl-all-in-one-xlnet-for-multi-party","slug":"dialogxl-all-in-one-xlnet-for-multi-party","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","date":"2020-12-16","arxiv_id":"2012.08695","n_code_links":4,"syntology":null},{"paper":null,"slug":"focusing-more-on-conflicts-with-mis","title":"Learning from Mistakes: Using Mis-predictions as Harm Alerts in Language Pre-Training","date":"2020-12-16","arxiv_id":"2012.08789","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-2-net-relation-of-relation-learning-network","title":"R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching","date":"2020-12-16","arxiv_id":"2012.08920","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-linformer-with-a-modified-self","title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformers-as-energy-based-1","slug":"pre-training-transformers-as-energy-based-1","title":"Pre-Training Transformers as Energy-Based Cloze Models","date":"2020-12-15","arxiv_id":"2012.08561","n_code_links":1,"syntology":null},{"paper":null,"slug":"lrc-bert-latent-representation-contrastive","title":"LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding","date":"2020-12-14","arxiv_id":"2012.07335","n_code_links":0,"syntology":null},{"paper":null,"slug":"vartani-spellcheck-automatic-context","title":"Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance","date":"2020-12-14","arxiv_id":"2012.07652","n_code_links":0,"syntology":null},{"paper":null,"slug":"discriminative-pre-training-for-low-resource","title":"Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery","date":"2020-12-13","arxiv_id":"2012.06943","n_code_links":0,"syntology":null},{"paper":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","n_code_links":0,"syntology":null},{"paper":null,"slug":"minivlm-a-smaller-and-faster-vision-language","title":"MiniVLM: A Smaller and Faster Vision-Language Model","date":"2020-12-13","arxiv_id":"2012.06946","n_code_links":0,"syntology":null},{"paper":"/paper/cogalex-vi-shared-task-transrelation-a-robust","slug":"cogalex-vi-shared-task-transrelation-a-robust","title":"CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation Identification","date":"2020-12-12","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"6c7de76d0534d8592549625c84c002444ca7cf2bcaf14dc36c36bc4e064eb5f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}