{"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/weight-decay/papers/102","list_of":"/method/weight-decay","method":"Weight 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":102,"pages_in_order":108,"rows_per_page":100,"rows":[10101,10200],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"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/weight-decay","prev":"/method/weight-decay/papers/101","next":"/method/weight-decay/papers/103","papers":[{"paper":"/paper/phenotyping-of-clinical-notes-with-improved","slug":"phenotyping-of-clinical-notes-with-improved","title":"Phenotyping of Clinical Notes with Improved Document Classification Models Using Contextualized Neural Language Models","date":"2019-10-30","arxiv_id":"1910.13664","n_code_links":2,"syntology":null},{"paper":null,"slug":"time-to-take-emoji-seriously-they-vastly","title":"Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models","date":"2019-10-30","arxiv_id":"1910.13793","n_code_links":0,"syntology":null},{"paper":"/paper/191013291","slug":"191013291","title":"Sentence Embeddings for Russian NLU","date":"2019-10-29","arxiv_id":"1910.13291","n_code_links":1,"syntology":null},{"paper":"/paper/inducing-brain-relevant-bias-in-natural","slug":"inducing-brain-relevant-bias-in-natural","title":"Inducing brain-relevant bias in natural language processing models","date":"2019-10-29","arxiv_id":"1911.03268","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["danrsc/bert_brain_neurips_2019"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"learning-rich-image-region-representation-for","title":"Learning Rich Image Region Representation for Visual Question Answering","date":"2019-10-29","arxiv_id":"1910.13077","n_code_links":0,"syntology":null},{"paper":"/paper/a-bert-based-transfer-learning-approach-for","slug":"a-bert-based-transfer-learning-approach-for","title":"A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media","date":"2019-10-28","arxiv_id":"1910.12574","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/a-simple-but-effective-bert-model-for-dialog","slug":"a-simple-but-effective-bert-model-for-dialog","title":"A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems","date":"2019-10-28","arxiv_id":"1910.12995","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-automatic-speech","slug":"sequence-to-sequence-automatic-speech","title":"Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding","date":"2019-10-28","arxiv_id":"1910.12740","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-from-multiple-choice","title":"What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?","date":"2019-10-28","arxiv_id":"1910.12391","n_code_links":0,"syntology":null},{"paper":"/paper/open-the-boxes-of-words-incorporating-sememes","slug":"open-the-boxes-of-words-incorporating-sememes","title":"Word-level Textual Adversarial Attacking as Combinatorial Optimization","date":"2019-10-27","arxiv_id":"1910.12196","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 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) · 1 unverified","official":{"repos":["thunlp/SememePSO-Attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/thieves-on-sesame-street-model-extraction-of","slug":"thieves-on-sesame-street-model-extraction-of","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","date":"2019-10-27","arxiv_id":"1910.12366","n_code_links":1,"syntology":null},{"paper":null,"slug":"dens-a-dataset-for-multi-class-emotion","title":"DENS: A Dataset for Multi-class Emotion Analysis","date":"2019-10-25","arxiv_id":"1910.11769","n_code_links":0,"syntology":null},{"paper":"/paper/hubert-untangles-bert-to-improve-transfer-1","slug":"hubert-untangles-bert-to-improve-transfer-1","title":"HUBERT Untangles BERT to Improve Transfer across NLP Tasks","date":"2019-10-25","arxiv_id":"1910.12647","n_code_links":1,"syntology":null},{"paper":null,"slug":"l2rs-a-learning-to-rescore-mechanism-for","title":"L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11496","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-cross-lingual-transferability-of","slug":"on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","date":"2019-10-25","arxiv_id":"1910.11856","n_code_links":7,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["deepmind/xquad"],"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/speechbert-cross-modal-pre-trained-language","slug":"speechbert-cross-modal-pre-trained-language","title":"SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering","date":"2019-10-25","arxiv_id":"1910.11559","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-efficient-asr-rescoring","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","date":"2019-10-24","arxiv_id":"1910.11450","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-acoustics-content-and-interaction","title":"Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings","date":"2019-10-24","arxiv_id":"1910.10869","n_code_links":0,"syntology":null},{"paper":null,"slug":"emergent-properties-of-finetuned-language","title":"Emergent Properties of Finetuned Language Representation Models","date":"2019-10-23","arxiv_id":"1910.10832","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-transformers-for-long-document","slug":"hierarchical-transformers-for-long-document","title":"Hierarchical Transformers for Long Document Classification","date":"2019-10-23","arxiv_id":"1910.10781","n_code_links":3,"syntology":null},{"paper":null,"slug":"relation-module-for-non-answerable-prediction","title":"Relation Module for Non-answerable Prediction on Question Answering","date":"2019-10-23","arxiv_id":"1910.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-xlnet-unsupervised-acoustic-model","title":"Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks","date":"2019-10-23","arxiv_id":"1910.10387","n_code_links":0,"syntology":null},{"paper":"/paper/mrqa-2019-shared-task-evaluating","slug":"mrqa-2019-shared-task-evaluating","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","date":"2019-10-22","arxiv_id":"1910.09753","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mrqa/MRQA-Shared-Task-2019"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/monalog-a-lightweight-system-for-natural","slug":"monalog-a-lightweight-system-for-natural","title":"MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity","date":"2019-10-19","arxiv_id":"1910.08772","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-mutual-information-maximization-perspective-1","title":"A Mutual Information Maximization Perspective of Language Representation Learning","date":"2019-10-18","arxiv_id":"1910.08350","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-compression-with-two-stage-multi","title":"Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System","date":"2019-10-18","arxiv_id":"1910.08381","n_code_links":0,"syntology":null},{"paper":null,"slug":"big-mood-relating-transformers-to-explicit","title":"BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge","date":"2019-10-17","arxiv_id":"1910.07713","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-semantic-similarity-of-clinical","slug":"measuring-semantic-similarity-of-clinical","title":"Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations","date":"2019-10-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-text-representation-from-bert-an","title":"Universal Text Representation from BERT: An Empirical Study","date":"2019-10-17","arxiv_id":"1910.07973","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exponential-learning-rate-schedule-for-1","title":"An Exponential Learning Rate Schedule for Deep Learning","date":"2019-10-16","arxiv_id":"1910.07454","n_code_links":0,"syntology":null},{"paper":"/paper/bertram-improved-word-embeddings-have-big","slug":"bertram-improved-word-embeddings-have-big","title":"BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance","date":"2019-10-16","arxiv_id":"1910.07181","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["timoschick/bertram"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-the-knowledge-gap-enhancing-question","title":"Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge","date":"2019-10-16","arxiv_id":"1910.07429","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-cross-lingual-entities-with-multi","slug":"aligning-cross-lingual-entities-with-multi","title":"Aligning Cross-Lingual Entities with Multi-Aspect Information","date":"2019-10-15","arxiv_id":"1910.06575","n_code_links":1,"syntology":null},{"paper":"/paper/answering-complex-open-domain-questions","slug":"answering-complex-open-domain-questions","title":"Answering Complex Open-domain Questions Through Iterative Query Generation","date":"2019-10-15","arxiv_id":"1910.07000","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qipeng/golden-retriever"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pruning-a-bert-based-question-answering-model","title":"Structured Pruning of a BERT-based Question Answering Model","date":"2019-10-14","arxiv_id":"1910.06360","n_code_links":0,"syntology":null},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","n_code_links":5,"syntology":{"ran":10,"of":11,"n_ran_checked":9,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/stancy-stance-classification-based-on","slug":"stancy-stance-classification-based-on","title":"STANCY: Stance Classification Based on Consistency Cues","date":"2019-10-14","arxiv_id":"1910.06048","n_code_links":1,"syntology":null},{"paper":"/paper/whatcha-lookin-at-deeplifting-berts-attention","slug":"whatcha-lookin-at-deeplifting-berts-attention","title":"Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering","date":"2019-10-14","arxiv_id":"1910.06431","n_code_links":1,"syntology":null},{"paper":null,"slug":"progress-notes-classification-and-keyword","title":"Progress Notes Classification and Keyword Extraction using Attention-based Deep Learning Models with BERT","date":"2019-10-13","arxiv_id":"1910.05786","n_code_links":0,"syntology":null},{"paper":"/paper/vq-wav2vec-self-supervised-learning-of-1","slug":"vq-wav2vec-self-supervised-learning-of-1","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","date":"2019-10-12","arxiv_id":"1910.05453","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"automatic-segmentation-of-texts-into-units-of","title":"Automatic segmentation of texts into units of meaning for reading assistance","date":"2019-10-11","arxiv_id":"1910.05014","n_code_links":0,"syntology":null},{"paper":"/paper/bipar-a-bilingual-parallel-dataset-for","slug":"bipar-a-bilingual-parallel-dataset-for","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","date":"2019-10-11","arxiv_id":"1910.05040","n_code_links":1,"syntology":null},{"paper":"/paper/exbert-a-visual-analysis-tool-to-explore","slug":"exbert-a-visual-analysis-tool-to-explore","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","date":"2019-10-11","arxiv_id":"1910.05276","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-alignment-vs-joint-training-a","slug":"cross-lingual-alignment-vs-joint-training-a","title":"Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework","date":"2019-10-10","arxiv_id":"1910.04708","n_code_links":2,"syntology":null},{"paper":"/paper/fuse-multi-faceted-set-expansion-by-coherent","slug":"fuse-multi-faceted-set-expansion-by-coherent","title":"FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams","date":"2019-10-10","arxiv_id":"1910.04345","n_code_links":3,"syntology":null},{"paper":"/paper/multi-label-categorization-of-accounts-of","slug":"multi-label-categorization-of-accounts-of","title":"Multi-label Categorization of Accounts of Sexism using a Neural Framework","date":"2019-10-10","arxiv_id":"1910.04602","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-question-answering-from","title":"Multilingual Question Answering from Formatted Text applied to Conversational Agents","date":"2019-10-10","arxiv_id":"1910.04659","n_code_links":0,"syntology":null},{"paper":"/paper/structured-pruning-of-large-language-models","slug":"structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","date":"2019-10-10","arxiv_id":"1910.04732","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["asappresearch/flop"],"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/visual-natural-language-query-auto-completion","slug":"visual-natural-language-query-auto-completion","title":"Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities","date":"2019-10-10","arxiv_id":"1910.04887","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-closer-look-at-feature-space-data","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","date":"2019-10-09","arxiv_id":"1910.04176","n_code_links":0,"syntology":null},{"paper":"/paper/alternating-recurrent-dialog-model-with-large","slug":"alternating-recurrent-dialog-model-with-large","title":"Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models","date":"2019-10-09","arxiv_id":"1910.03756","n_code_links":1,"syntology":null},{"paper":null,"slug":"ctrl-z-recovering-from-instability-in","title":"Ctrl-Z: Recovering from Instability in Reinforcement Learning","date":"2019-10-09","arxiv_id":"1910.03732","n_code_links":0,"syntology":null},{"paper":"/paper/is-multilingual-bert-fluent-in-language","slug":"is-multilingual-bert-fluent-in-language","title":"Is Multilingual BERT Fluent in Language Generation?","date":"2019-10-09","arxiv_id":"1910.03806","n_code_links":1,"syntology":null},{"paper":"/paper/eca-net-efficient-channel-attention-for-deep","slug":"eca-net-efficient-channel-attention-for-deep","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","date":"2019-10-08","arxiv_id":"1910.03151","n_code_links":13,"syntology":{"ran":3,"of":8,"n_ran_checked":2,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["BangguWu/ECANet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-distillation-from-internal","title":"Knowledge Distillation from Internal Representations","date":"2019-10-08","arxiv_id":"1910.03723","n_code_links":0,"syntology":null},{"paper":null,"slug":"sesamebert-attention-for-anywhere","title":"SesameBERT: Attention for Anywhere","date":"2019-10-08","arxiv_id":"1910.03176","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-evidence-retrieval-and-claim","slug":"bert-for-evidence-retrieval-and-claim","title":"BERT for Evidence Retrieval and Claim Verification","date":"2019-10-07","arxiv_id":"1910.02655","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/deformable-kernels-adapting-effective","slug":"deformable-kernels-adapting-effective","title":"Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation","date":"2019-10-07","arxiv_id":"1910.02940","n_code_links":2,"syntology":null},{"paper":"/paper/parallel-iterative-edit-models-for-local","slug":"parallel-iterative-edit-models-for-local","title":"Parallel Iterative Edit Models for Local Sequence Transduction","date":"2019-10-07","arxiv_id":"1910.02893","n_code_links":1,"syntology":null},{"paper":"/paper/named-entity-recognition-is-there-a-glass","slug":"named-entity-recognition-is-there-a-glass","title":"Named Entity Recognition -- Is there a glass ceiling?","date":"2019-10-06","arxiv_id":"1910.02403","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-transformers-into-simple-neural","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","date":"2019-10-04","arxiv_id":"1910.01769","n_code_links":0,"syntology":null},{"paper":"/paper/fine-grained-sentiment-classification-using","slug":"fine-grained-sentiment-classification-using","title":"Fine-grained Sentiment Classification using BERT","date":"2019-10-04","arxiv_id":"1910.03474","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: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","n_code_links":10,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"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/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","n_code_links":1,"syntology":null},{"paper":null,"slug":"cracking-the-contextual-commonsense-code","title":"Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations","date":"2019-10-02","arxiv_id":"1910.01157","n_code_links":0,"syntology":null},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","n_code_links":37,"syntology":{"ran":21,"of":27,"n_ran_checked":13,"n_instrument":8,"unverified":6,"pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/exploiting-bert-for-end-to-end-aspect-based","slug":"exploiting-bert-for-end-to-end-aspect-based","title":"Exploiting BERT for End-to-End Aspect-based Sentiment Analysis","date":"2019-10-02","arxiv_id":"1910.00883","n_code_links":1,"syntology":null},{"paper":"/paper/linking-artificial-and-human-neural","slug":"linking-artificial-and-human-neural","title":"Linking artificial and human neural representations of language","date":"2019-10-02","arxiv_id":"1910.01244","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"8 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; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/quantized-reinforcement-learning-quarl","slug":"quantized-reinforcement-learning-quarl","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","date":"2019-10-02","arxiv_id":"1910.01055","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["harvard-edge/quarl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-for-question-generation","title":"BERT for Question Generation","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/specializing-word-embeddings-for-parsing-by","slug":"specializing-word-embeddings-for-parsing-by","title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","date":"2019-10-01","arxiv_id":"1910.00163","n_code_links":1,"syntology":null},{"paper":null,"slug":"tmlab-generative-enhanced-model-gem-for","title":"TMLab: Generative Enhanced Model (GEM) for adversarial attacks","date":"2019-10-01","arxiv_id":"1910.00337","n_code_links":0,"syntology":null},{"paper":null,"slug":"vae-pgn-based-abstractive-model-in-multi","title":"VAE-PGN based Abstractive Model in Multi-stage Architecture for Text Summarization","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-resume-parsing-and-finding","title":"End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT","date":"2019-09-30","arxiv_id":"1910.03089","n_code_links":0,"syntology":null},{"paper":"/paper/randaugment-practical-data-augmentation-with","slug":"randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","arxiv_id":"1909.13719","n_code_links":19,"syntology":{"ran":58,"of":65,"n_ran_checked":7,"n_instrument":51,"unverified":7,"pointer_only":17,"phrase":"58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/fake-news-detection-using-deep-learning","slug":"fake-news-detection-using-deep-learning","title":"Fake news detection using Deep Learning","date":"2019-09-29","arxiv_id":"1910.03496","n_code_links":2,"syntology":null},{"paper":"/paper/global-sparse-momentum-sgd-for-pruning-very","slug":"global-sparse-momentum-sgd-for-pruning-very","title":"Global Sparse Momentum SGD for Pruning Very Deep Neural Networks","date":"2019-09-27","arxiv_id":"1909.12778","n_code_links":4,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["DingXiaoH/GSM-SGD"],"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/hatemonitors-language-agnostic-abuse","slug":"hatemonitors-language-agnostic-abuse","title":"HateMonitors: Language Agnostic Abuse Detection in Social Media","date":"2019-09-27","arxiv_id":"1909.12642","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-use-of-bert-for-neural-machine","title":"On the use of BERT for Neural Machine Translation","date":"2019-09-27","arxiv_id":"1909.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"reweighted-proximal-pruning-for-large-scale-1","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","date":"2019-09-27","arxiv_id":"1909.12486","n_code_links":0,"syntology":null},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","n_code_links":48,"syntology":{"ran":81,"of":126,"n_ran_checked":59,"n_instrument":22,"unverified":45,"pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 59 with no instrument failure: 4 honoured, 0 violated, 55 with no contract checked; 22 where Syntology's instrument failed) · 45 unverified","official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"aspect-and-opinion-term-extraction-for-aspect","title":"Aspect and Opinion Term Extraction for Hotel Reviews using Transfer Learning and Auxiliary Labels","date":"2019-09-26","arxiv_id":"1909.11879","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-relation-extraction-with-pre","title":"Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture","date":"2019-09-26","arxiv_id":"1909.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-detect-opinion-snippet-for-aspect","title":"Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis","date":"2019-09-25","arxiv_id":"1909.11297","n_code_links":0,"syntology":null},{"paper":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","n_code_links":2,"syntology":null},{"paper":null,"slug":"technical-report-on-conversational-question","title":"Technical report on Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10772","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","n_code_links":0,"syntology":null},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/190910430","slug":"190910430","title":"Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings","date":"2019-09-23","arxiv_id":"1909.10430","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-identification-and-normalisation-of","slug":"automatic-identification-and-normalisation-of","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"constrained-attractor-selection-using-deep","title":"Constrained Attractor Selection Using Deep Reinforcement Learning","date":"2019-09-23","arxiv_id":"1909.10500","n_code_links":0,"syntology":null},{"paper":"/paper/portuguese-named-entity-recognition-using-1","slug":"portuguese-named-entity-recognition-using-1","title":"Portuguese Named Entity Recognition using BERT-CRF","date":"2019-09-23","arxiv_id":"1909.10649","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["neuralmind-ai/portuguese-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","n_code_links":0,"syntology":null},{"paper":null,"slug":"absum-simple-regularization-method-for","title":"Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks","date":"2019-09-19","arxiv_id":"1909.08830","n_code_links":0,"syntology":null},{"paper":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","n_code_links":0,"syntology":null}],"record_sha256":"feb4f654ee106f126e8d83f0ca219e5d43ff41b7e4aaec0c143c855ac5a81d1e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}