{"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/layer-normalization/papers/221","list_of":"/method/layer-normalization","method":"Layer Normalization","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":221,"pages_in_order":250,"rows_per_page":100,"rows":[22001,22100],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/220","next":"/method/layer-normalization/papers/222","papers":[{"paper":null,"slug":"persuasive-dialogue-understanding-the","title":"Persuasive Dialogue Understanding: the Baselines and Negative Results","date":"2020-11-19","arxiv_id":"2011.09954","n_code_links":0,"syntology":null},{"paper":null,"slug":"reassert-deep-learning-for-assert-generation","title":"ReAssert: Deep Learning for Assert Generation","date":"2020-11-19","arxiv_id":"2011.09784","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-and-non-redundant-answer-set","title":"Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs","date":"2020-11-18","arxiv_id":"2011.09140","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-fine-tuned-commonsense-language-models","title":"Do Fine-tuned Commonsense Language Models Really Generalize?","date":"2020-11-18","arxiv_id":"2011.09159","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-object-detection-with-adaptive","slug":"end-to-end-object-detection-with-adaptive","title":"End-to-End Object Detection with Adaptive Clustering Transformer","date":"2020-11-18","arxiv_id":"2011.09315","n_code_links":1,"syntology":null},{"paper":null,"slug":"palomino-ochoa-at-semeval-2020-task-9-robust","title":"Palomino-Ochoa at SemEval-2020 Task 9: Robust System based on Transformer for Code-Mixed Sentiment Classification","date":"2020-11-18","arxiv_id":"2011.09448","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-level-mixed-sample-data-augmentation","slug":"sequence-level-mixed-sample-data-augmentation","title":"Sequence-Level Mixed Sample Data Augmentation","date":"2020-11-18","arxiv_id":"2011.09039","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-ubiqus-english-inuktitut-system-for-wmt20","title":"The Ubiqus English-Inuktitut System for WMT20","date":"2020-11-18","arxiv_id":"2011.09249","n_code_links":0,"syntology":null},{"paper":null,"slug":"tie-your-embeddings-down-cross-modal-latent","title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","date":"2020-11-18","arxiv_id":"2011.09044","n_code_links":0,"syntology":null},{"paper":"/paper/up-detr-unsupervised-pre-training-for-object","slug":"up-detr-unsupervised-pre-training-for-object","title":"UP-DETR: Unsupervised Pre-training for Object Detection with Transformers","date":"2020-11-18","arxiv_id":"2011.09094","n_code_links":2,"syntology":null},{"paper":null,"slug":"attention-mechanism-transformers-bert-and-gpt","title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","date":"2020-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mvp-bert-redesigning-vocabularies-for-chinese-1","title":"MVP-BERT: Redesigning Vocabularies for Chinese BERT and Multi-Vocab Pretraining","date":"2020-11-17","arxiv_id":"2011.08539","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-learning-of-galaxy-morphology","title":"Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders","date":"2020-11-17","arxiv_id":"2011.08714","n_code_links":0,"syntology":null},{"paper":"/paper/siena-stochastic-multi-expert-neural-patcher","slug":"siena-stochastic-multi-expert-neural-patcher","title":"SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","date":"2020-11-17","arxiv_id":"2011.08908","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-i-i-d-three-levels-of-generalization","slug":"beyond-i-i-d-three-levels-of-generalization","title":"Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases","date":"2020-11-16","arxiv_id":"2011.07743","n_code_links":1,"syntology":null},{"paper":null,"slug":"don-t-patronize-me-an-annotated-dataset-with","title":"Don't Patronize Me! An Annotated Dataset with Patronizing and Condescending Language towards Vulnerable Communities","date":"2020-11-16","arxiv_id":"2011.08320","n_code_links":0,"syntology":null},{"paper":null,"slug":"iit-kgp-at-fincausal-2020-shared-task-1","title":"IIT_kgp at FinCausal 2020, Shared Task 1: Causality Detection using Sentence Embeddings in Financial Reports","date":"2020-11-16","arxiv_id":"2011.07670","n_code_links":0,"syntology":null},{"paper":"/paper/it-s-a-thin-line-between-love-and-hate-using","slug":"it-s-a-thin-line-between-love-and-hate-using","title":"It's a Thin Line Between Love and Hate: Using the Echo in Modeling Dynamics of Racist Online Communities","date":"2020-11-16","arxiv_id":"2012.01133","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-task-descriptions","slug":"learning-from-task-descriptions","title":"Learning from Task Descriptions","date":"2020-11-16","arxiv_id":"2011.08115","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/on-the-effectiveness-of-vision-transformers","slug":"on-the-effectiveness-of-vision-transformers","title":"On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing","date":"2020-11-16","arxiv_id":"2011.08019","n_code_links":1,"syntology":null},{"paper":"/paper/actbert-learning-global-local-video-text-1","slug":"actbert-learning-global-local-video-text-1","title":"ActBERT: Learning Global-Local Video-Text Representations","date":"2020-11-14","arxiv_id":"2011.07231","n_code_links":1,"syntology":null},{"paper":"/paper/cl-ims-diacr-ita-volente-o-nolente-bert-does","slug":"cl-ims-diacr-ita-volente-o-nolente-bert-does","title":"CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection","date":"2020-11-14","arxiv_id":"2011.07247","n_code_links":1,"syntology":null},{"paper":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","n_code_links":3,"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":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"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/utilizing-bidirectional-encoder","slug":"utilizing-bidirectional-encoder","title":"Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection","date":"2020-11-14","arxiv_id":"2011.07208","n_code_links":1,"syntology":null},{"paper":"/paper/editor-an-edit-based-transformer-with","slug":"editor-an-edit-based-transformer-with","title":"EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints","date":"2020-11-13","arxiv_id":"2011.06868","n_code_links":1,"syntology":null},{"paper":"/paper/flert-document-level-features-for-named","slug":"flert-document-level-features-for-named","title":"FLERT: Document-Level Features for Named Entity Recognition","date":"2020-11-13","arxiv_id":"2011.06993","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-modal-emotion-detection-with-transfer","title":"Multi-Modal Emotion Detection with Transfer Learning","date":"2020-11-13","arxiv_id":"2011.07065","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-interpretable-end-to-end-fine-tuning","title":"An Interpretable End-to-end Fine-tuning Approach for Long Clinical Text","date":"2020-11-12","arxiv_id":"2011.06504","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-bert-carefully-with","title":"Augmenting BERT Carefully with Underrepresented Linguistic Features","date":"2020-11-12","arxiv_id":"2011.06153","n_code_links":0,"syntology":null},{"paper":"/paper/author-s-sentiment-prediction","slug":"author-s-sentiment-prediction","title":"Author's Sentiment Prediction","date":"2020-11-12","arxiv_id":"2011.06128","n_code_links":1,"syntology":null},{"paper":"/paper/biomedical-named-entity-recognition-at-scale","slug":"biomedical-named-entity-recognition-at-scale","title":"Biomedical Named Entity Recognition at Scale","date":"2020-11-12","arxiv_id":"2011.06315","n_code_links":1,"syntology":null},{"paper":null,"slug":"identifying-depressive-symptoms-from-tweets","title":"Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework","date":"2020-11-12","arxiv_id":"2011.06149","n_code_links":0,"syntology":null},{"paper":"/paper/hurricane-forecasting-a-novel-multimodal","slug":"hurricane-forecasting-a-novel-multimodal","title":"Hurricane Forecasting: A Novel Multimodal Machine Learning Framework","date":"2020-11-11","arxiv_id":"2011.06125","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["leobix/hurricast"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/multilingual-irony-detection-with-dependency","slug":"multilingual-irony-detection-with-dependency","title":"Multilingual Irony Detection with Dependency Syntax and Neural Models","date":"2020-11-11","arxiv_id":"2011.05706","n_code_links":1,"syntology":null},{"paper":null,"slug":"nit-covid-19-at-wnut-2020-task-2-deep","title":"NIT COVID-19 at WNUT-2020 Task 2: Deep Learning Model RoBERTa for Identify Informative COVID-19 English Tweets","date":"2020-11-11","arxiv_id":"2011.05551","n_code_links":0,"syntology":null},{"paper":null,"slug":"recognizing-more-emotions-with-less-data","title":"Recognizing More Emotions with Less Data Using Self-supervised Transfer Learning","date":"2020-11-11","arxiv_id":"2011.05585","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-semi-supervised-semantics","title":"Towards Semi-Supervised Semantics Understanding from Speech","date":"2020-11-11","arxiv_id":"2011.06195","n_code_links":0,"syntology":null},{"paper":null,"slug":"trailer-transformer-based-time-wise-long-term","title":"TERMCast: Temporal Relation Modeling for Effective Urban Flow Forecasting","date":"2020-11-11","arxiv_id":"2011.05554","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-systematic-comparison-of-encrypted-machine","title":"A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification","date":"2020-11-10","arxiv_id":"2011.05296","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-social-media-manipulation-in-low","title":"Detecting Social Media Manipulation in Low-Resource Languages","date":"2020-11-10","arxiv_id":"2011.05367","n_code_links":0,"syntology":null},{"paper":null,"slug":"e-t-entity-transformers-coreference-augmented","title":"E.T.: Entity-Transformers. Coreference augmented Neural Language Model for richer mention representations via Entity-Transformer blocks","date":"2020-11-10","arxiv_id":"2011.05431","n_code_links":0,"syntology":null},{"paper":"/paper/umberto-mtsa-accompl-it-improving-complexity","slug":"umberto-mtsa-accompl-it-improving-complexity","title":"UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations","date":"2020-11-10","arxiv_id":"2011.05197","n_code_links":1,"syntology":null},{"paper":"/paper/when-do-you-need-billions-of-words-of","slug":"when-do-you-need-billions-of-words-of","title":"When Do You Need Billions of Words of Pretraining Data?","date":"2020-11-10","arxiv_id":"2011.04946","n_code_links":1,"syntology":null},{"paper":"/paper/bangla-text-classification-using-transformers","slug":"bangla-text-classification-using-transformers","title":"Bangla Text Classification using Transformers","date":"2020-11-09","arxiv_id":"2011.04446","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-jam-boosting-bert-enhanced-neural","title":"BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention","date":"2020-11-09","arxiv_id":"2011.04266","n_code_links":0,"syntology":null},{"paper":null,"slug":"catch-the-tails-of-bert","title":"Positional Artefacts Propagate Through Masked Language Model Embeddings","date":"2020-11-09","arxiv_id":"2011.04393","n_code_links":0,"syntology":null},{"paper":"/paper/cxgbert-bert-meets-construction-grammar","slug":"cxgbert-bert-meets-construction-grammar","title":"CxGBERT: BERT meets Construction Grammar","date":"2020-11-09","arxiv_id":"2011.04134","n_code_links":1,"syntology":null},{"paper":null,"slug":"estbert-a-pretrained-language-specific-bert","title":"EstBERT: A Pretrained Language-Specific BERT for Estonian","date":"2020-11-09","arxiv_id":"2011.04784","n_code_links":0,"syntology":null},{"paper":"/paper/language-through-a-prism-a-spectral-approach","slug":"language-through-a-prism-a-spectral-approach","title":"Language Through a Prism: A Spectral Approach for Multiscale Language Representations","date":"2020-11-09","arxiv_id":"2011.04823","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":null}},{"paper":"/paper/magneto-an-efficient-deep-learning-method-for-1","slug":"magneto-an-efficient-deep-learning-method-for-1","title":"MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem","date":"2020-11-09","arxiv_id":"2011.04349","n_code_links":1,"syntology":null},{"paper":"/paper/visbert-hidden-state-visualizations-for","slug":"visbert-hidden-state-visualizations-for","title":"VisBERT: Hidden-State Visualizations for Transformers","date":"2020-11-09","arxiv_id":"2011.04507","n_code_links":1,"syntology":null},{"paper":"/paper/adapting-a-language-model-for-controlled","slug":"adapting-a-language-model-for-controlled","title":"Adapting a Language Model for Controlled Affective Text Generation","date":"2020-11-08","arxiv_id":"2011.04000","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["ishikasingh/Affective-text-gen"],"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","unlocated"]}}},{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","slug":"indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/long-range-arena-a-benchmark-for-efficient-1","slug":"long-range-arena-a-benchmark-for-efficient-1","title":"Long Range Arena: A Benchmark for Efficient Transformers","date":"2020-11-08","arxiv_id":"2011.04006","n_code_links":5,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/long-range-arena"],"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/stochastic-attention-head-removal-a-simple","slug":"stochastic-attention-head-removal-a-simple","title":"Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models","date":"2020-11-08","arxiv_id":"2011.04004","n_code_links":5,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["s1603602/attention_head_removal"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"know-what-you-don-t-need-single-shot-meta","title":"Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads","date":"2020-11-07","arxiv_id":"2011.03770","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-the-value-of-transformer","title":"Rethinking the Value of Transformer Components","date":"2020-11-07","arxiv_id":"2011.03803","n_code_links":0,"syntology":null},{"paper":"/paper/seqgensql-a-robust-sequence-generation-model","slug":"seqgensql-a-robust-sequence-generation-model","title":"SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language","date":"2020-11-07","arxiv_id":"2011.03836","n_code_links":2,"syntology":null},{"paper":"/paper/from-dataset-recycling-to-multi-property","slug":"from-dataset-recycling-to-multi-property","title":"From Dataset Recycling to Multi-Property Extraction and Beyond","date":"2020-11-06","arxiv_id":"2011.03228","n_code_links":1,"syntology":null},{"paper":null,"slug":"highly-available-data-parallel-ml-training-on","title":"Highly Available Data Parallel ML training on Mesh Networks","date":"2020-11-06","arxiv_id":"2011.03605","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-prosody-modelling-with-cross","title":"Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis","date":"2020-11-06","arxiv_id":"2011.05161","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-low-resource-style-transfer","slug":"semi-supervised-low-resource-style-transfer","title":"Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation","date":"2020-11-06","arxiv_id":"2011.03286","n_code_links":1,"syntology":null},{"paper":null,"slug":"bw-eda-eend-streaming-end-to-end-neural","title":"BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers","date":"2020-11-05","arxiv_id":"2011.02678","n_code_links":0,"syntology":null},{"paper":"/paper/coder-knowledge-infused-cross-lingual-medical","slug":"coder-knowledge-infused-cross-lingual-medical","title":"CODER: Knowledge infused cross-lingual medical term embedding for term normalization","date":"2020-11-05","arxiv_id":"2011.02947","n_code_links":1,"syntology":null},{"paper":"/paper/nuaa-qmul-at-semeval-2020-task-8-utilizing","slug":"nuaa-qmul-at-semeval-2020-task-8-utilizing","title":"NUAA-QMUL at SemEval-2020 Task 8: Utilizing BERT and DenseNet for Internet Meme Emotion Analysis","date":"2020-11-05","arxiv_id":"2011.02788","n_code_links":1,"syntology":null},{"paper":"/paper/indic-transformers-an-analysis-of-transformer","slug":"indic-transformers-an-analysis-of-transformer","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","date":"2020-11-04","arxiv_id":"2011.02323","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-novel-verb-learning-in-bert","slug":"investigating-novel-verb-learning-in-bert","title":"Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization","date":"2020-11-04","arxiv_id":"2011.02417","n_code_links":1,"syntology":null},{"paper":"/paper/mtlb-struct-parseme-2020-capturing-unseen","slug":"mtlb-struct-parseme-2020-capturing-unseen","title":"MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models","date":"2020-11-04","arxiv_id":"2011.02541","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-transformer-for-low-resource","title":"Optimizing Transformer for Low-Resource Neural Machine Translation","date":"2020-11-04","arxiv_id":"2011.02266","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-multilingual-bert-for-genetic-and","title":"Probing Multilingual BERT for Genetic and Typological Signals","date":"2020-11-04","arxiv_id":"2011.02070","n_code_links":0,"syntology":null},{"paper":null,"slug":"prosodic-representation-learning-and","title":"Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech","date":"2020-11-04","arxiv_id":"2011.02252","n_code_links":0,"syntology":null},{"paper":"/paper/bionerflair-biomedical-named-entity","slug":"bionerflair-biomedical-named-entity","title":"BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger","date":"2020-11-03","arxiv_id":"2011.01504","n_code_links":1,"syntology":null},{"paper":"/paper/charbert-character-aware-pre-trained-language","slug":"charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","arxiv_id":"2011.01513","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["wtma/CharBERT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/finding-friends-and-flipping-frenemies","slug":"finding-friends-and-flipping-frenemies","title":"Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory","date":"2020-11-03","arxiv_id":"2011.01856","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hannahxchen/automatic-paraphrase-dataset-augmentation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-synthetic-data-for-task-oriented","title":"Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations","date":"2020-11-03","arxiv_id":"2011.02050","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-rnn-transducer-with-normalized","title":"Improving RNN transducer with normalized jointer network","date":"2020-11-03","arxiv_id":"2011.01576","n_code_links":0,"syntology":null},{"paper":"/paper/sound-natural-content-rephrasing-in-dialog","slug":"sound-natural-content-rephrasing-in-dialog","title":"Sound Natural: Content Rephrasing in Dialog Systems","date":"2020-11-03","arxiv_id":"2011.01993","n_code_links":1,"syntology":null},{"paper":"/paper/tabular-transformers-for-modeling","slug":"tabular-transformers-for-modeling","title":"Tabular Transformers for Modeling Multivariate Time Series","date":"2020-11-03","arxiv_id":"2011.01843","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["IBM/TabFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/xed-a-multilingual-dataset-for-sentiment","slug":"xed-a-multilingual-dataset-for-sentiment","title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","date":"2020-11-03","arxiv_id":"2011.01612","n_code_links":1,"syntology":null},{"paper":"/paper/a-closer-look-at-linguistic-knowledge-in","slug":"a-closer-look-at-linguistic-knowledge-in","title":"A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English","date":"2020-11-02","arxiv_id":"2011.00960","n_code_links":1,"syntology":null},{"paper":"/paper/abnirml-analyzing-the-behavior-of-neural-ir","slug":"abnirml-analyzing-the-behavior-of-neural-ir","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","date":"2020-11-02","arxiv_id":"2011.00696","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["allenai/abnirml"],"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":["official"]}}},{"paper":null,"slug":"abstracting-influence-paths-for-explaining-1","title":"Influence Patterns for Explaining Information Flow in BERT","date":"2020-11-02","arxiv_id":"2011.00740","n_code_links":0,"syntology":null},{"paper":"/paper/dual-decoder-transformer-for-joint-automatic","slug":"dual-decoder-transformer-for-joint-automatic","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","date":"2020-11-02","arxiv_id":"2011.00747","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-far-does-bert-look-at-distance-based","title":"How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention","date":"2020-11-02","arxiv_id":"2011.00943","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-various-semantic-models-for","slug":"introducing-various-semantic-models-for","title":"Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets","date":"2020-11-02","arxiv_id":"2011.01154","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-sentence-embeddings-from-pre-trained","slug":"on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","arxiv_id":"2011.05864","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: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bohanli/BERT-flow"],"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":"/paper/point-transformer","slug":"point-transformer","title":"Point Transformer","date":"2020-11-02","arxiv_id":"2011.00931","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["engelnico/point-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"qmul-sds-at-sardistance2020-leveraging","title":"QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs","date":"2020-11-02","arxiv_id":"2011.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semantics-based-approach-to-disclosure","title":"A Semantics-based Approach to Disclosure Classification in User-Generated Online Content","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structure-enhanced-graph-convolutional","title":"A structure-enhanced graph convolutional network for sentiment analysis","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-approaches-to-enhancing","title":"Active Learning Approaches to Enhancing Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/approximation-of-response-knowledge-retrieval","slug":"approximation-of-response-knowledge-retrieval","title":"Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/chime-cross-passage-hierarchical-memory","slug":"chime-cross-passage-hierarchical-memory","title":"CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering","date":"2020-11-01","arxiv_id":"2011.00519","n_code_links":1,"syntology":null},{"paper":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"context-analysis-for-pre-trained-masked","title":"Context Analysis for Pre-trained Masked Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gingsi/coot-videotext"],"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":["official"]}}},{"paper":null,"slug":"cross-lingual-training-of-neural-models-for","title":"Cross-Lingual Training of Neural Models for Document Ranking","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/decoding-language-spatial-relations-to-2d","slug":"decoding-language-spatial-relations-to-2d","title":"Decoding Language Spatial Relations to 2D Spatial Arrangements","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-generalization-in-natural-language","slug":"enhancing-generalization-in-natural-language","title":"Enhancing Generalization in Natural Language Inference by Syntax","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exbert-extending-pre-trained-models-with","title":"exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"24886a2bee2b6214f854a4b731a1bd54796d03c9c9d4bd1ffa695dbbc74eafb3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}