{"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":"/task/language-modelling/papers/151","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":151,"pages_in_order":177,"rows_per_page":100,"rows":[15001,15100],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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":"/task/language-modelling","prev":"/task/language-modelling/papers/150","next":"/task/language-modelling/papers/152","papers":[{"url":null,"slug":"a-review-of-on-device-fully-neural-end-to-end","title":"A review of on-device fully neural end-to-end automatic speech recognition algorithms","date":"2020-12-14","arxiv_id":"2012.07974","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-captioning-using-pre-trained-large","title":"Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval","date":"2020-12-14","arxiv_id":"2012.07331","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"affecton-incorporating-affect-into-dialog","title":"AffectON: Incorporating Affect Into Dialog Generation","date":"2020-12-12","arxiv_id":"2012.06847","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-the-timescale-organization-of-neural-1","title":"Mapping the Timescale Organization of Neural Language Models","date":"2020-12-12","arxiv_id":"2012.06717","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomedbert-a-pre-trained-biomedical-language","title":"BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR","date":"2020-12-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-sense-language-modelling","title":"Multi-Sense Language Modelling","date":"2020-12-10","arxiv_id":"2012.05776","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-approach-to-abstractive","title":"Cross-lingual Transfer of Abstractive Summarizer to Less-resource Language","date":"2020-12-08","arxiv_id":"2012.04307","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-domain-knowledge-to-improve","title":"Incorporating Domain Knowledge To Improve Topic Segmentation Of Long MOOC Lecture Videos","date":"2020-12-08","arxiv_id":"2012.07589","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-efficient-multimodal-transformers-1","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","date":"2020-12-08","arxiv_id":"2012.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"kgplm-knowledge-guided-language-model-pre","title":"KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning","date":"2020-12-07","arxiv_id":"2012.03551","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-bert-for-low-resource-natural","title":"Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning","date":"2020-12-04","arxiv_id":"2012.02462","repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-text-based-games-with-common-sense","title":"Playing Text-Based Games with Common Sense","date":"2020-12-04","arxiv_id":"2012.02757","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-pretrained-transformers-towards","title":"RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation","date":"2020-12-04","arxiv_id":"2012.02469","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapt-and-adjust-overcoming-the-long-tail-1","title":"Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition","date":"2020-12-03","arxiv_id":"2012.01687","repositories_listed":0,"syntology":null},{"url":null,"slug":"circles-are-like-ellipses-or-ellipses-are","title":"Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning","date":"2020-12-03","arxiv_id":"2012.01631","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-with-diversified","title":"Federated Learning for Personalized Humor Recognition","date":"2020-12-03","arxiv_id":"2012.01675","repositories_listed":0,"syntology":null},{"url":null,"slug":"gottbert-a-pure-german-language-model","title":"GottBERT: a pure German Language Model","date":"2020-12-03","arxiv_id":"2012.02110","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-and-dataset-for-abstract-art","title":"A Framework and Dataset for Abstract Art Generation via CalligraphyGAN","date":"2020-12-02","arxiv_id":"2012.00744","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-generative-approach-to-native-language","title":"A Deep Generative Approach to Native Language Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-local-coherence-analysis-model-for","title":"A Neural Local Coherence Analysis Model for Clarity Text Scoring","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ad-lingua-text-classification-improves","title":"Ad Lingua: Text Classification Improves Symbolism Prediction in Image Advertisements","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amobee-at-semeval-2020-task-7-regularization","title":"Amobee at SemEval-2020 Task 7: Regularization of Language Model Based Classifiers","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabizi-language-models-for-sentiment","title":"Arabizi Language Models for Sentiment Analysis","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-assistance-for-academic-word-usage","title":"Automatic Assistance for Academic Word Usage","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bertaa-bert-fine-tuning-for-authorship","title":"BertAA : BERT fine-tuning for Authorship Attribution","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"buhscitu-at-semeval-2020-task-7-assessing","title":"Buhscitu at SemEval-2020 Task 7: Assessing Humour in Edited News Headlines Using Hand-Crafted Features and Online Knowledge Bases","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-hierarchically-disentangled-language","title":"Building Hierarchically Disentangled Language Models for Text Generation with Named Entities","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cardiff-university-at-semeval-2020-task-6","title":"Cardiff University at SemEval-2020 Task 6: Fine-tuning BERT for Domain-Specific Definition Classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-grammatical-error-diagnosis-with","title":"Chinese Grammatical Error Diagnosis with Graph Convolution Network and Multi-task Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clplm-character-level-pretrained-language","title":"CLPLM: Character Level Pretrained Language Model for ExtractingSupport Phrases for Sentiment Labels","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-federated","title":"Communication-Efficient Federated Distillation","date":"2020-12-01","arxiv_id":"2012.00632","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-text-normalisation-for","title":"Context-Aware Text Normalisation for Historical Dialects","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-augmentation-of-pretrained","title":"Contextual Augmentation of Pretrained Language Models for Emotion Recognition in Conversations","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-based-identification-of-verbs","title":"Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dapper-learning-domain-adapted-persona","title":"DAPPER: Learning Domain-Adapted Persona Representation Using Pretrained BERT and External Memory","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-model-for-manipuri-multiword","title":"Deep Neural Model for Manipuri Multiword Named Entity Recognition with Unsupervised Cluster Feature","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distill-and-replay-for-continual-language","title":"Distill and Replay for Continual Language Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-transfer-based-data-augmentation-for","title":"Domain Transfer based Data Augmentation for Neural Query Translation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"elmo-nb-at-semeval-2020-task-7-assessing","title":"ELMo-NB at SemEval-2020 Task 7: Assessing Sense of Humor in EditedNews Headlines Using ELMo and NB","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ethan-at-semeval-2020-task-5-modelling-causal-1","title":"ETHAN at SemEval-2020 Task 5: Modelling Causal Reasoning in Language Using Neuro-symbolic Cloud Computing","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-looping-effects-in-rnn-based","title":"Exploring Looping Effects in RNN-based Architectures","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-text-classification-with-edge","title":"Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"go-simple-and-pre-train-on-domain-specific","title":"Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gpols-a-contextual-graph-based-language-model","title":"GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hit-scir-at-semeval-2020-task-5-training-pre","title":"HIT-SCIR at SemEval-2020 Task 5: Training Pre-trained Language Model with Pseudo-labeling Data for Counterfactuals Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"homonym-normalisation-by-word-sense","title":"Homonym normalisation by word sense clustering: a case in Japanese","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"icompass-at-semeval-2020-task-12-from-a","title":"iCompass at SemEval-2020 Task 12: From a Syntax-ignorant N-gram Embeddings Model to a Deep Bidirectional Language Model","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"intermediate-self-supervised-learning-for","title":"Intermediate Self-supervised Learning for Machine Translation Quality Estimation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-learning-dynamics-of-bert-fine","title":"Investigating Learning Dynamics of BERT Fine-Tuning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"just-at-semeval-2020-task-11-detecting","title":"JUST at SemEval-2020 Task 11: Detecting Propaganda Techniques Using BERT Pre-trained Model","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lt3-at-semeval-2020-task-7-comparing-feature","title":"LT3 at SemEval-2020 Task 7: Comparing Feature-Based and Transformer-Based Approaches to Detect Funny Headlines","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-reasoner-at-semeval-2020-task-4-fine","title":"Masked Reasoner at SemEval-2020 Task 4: Fine-Tuning RoBERTa for Commonsense Reasoning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"merge-and-recognize-a-geometry-and-2d-context","title":"Merge and Recognize: A Geometry and 2D Context Aware Graph Model for Named Entity Recognition from Visual Documents","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mineriaunam-at-semeval-2020-task-3-predicting","title":"MineriaUNAM at SemEval-2020 Task 3: Predicting Contextual WordSimilarity Using a Centroid Based Approach and Word Embeddings","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-local-contexts-for-joint-dialogue","title":"Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multivitaminbooster-at-parseme-shared-task","title":"MultiVitaminBooster at PARSEME Shared Task 2020: Combining Window- and Dependency-Based Features with Multilingual Contextualised Word Embeddings for VMWE Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mxgra-at-semeval-2020-task-4-common-sense","title":"Mxgra at SemEval-2020 Task 4: Common Sense Making with Next Token Prediction","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-language-modeling-for-named-entity","title":"Neural Language Modeling for Named Entity Recognition","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-language-models-for-text","title":"Neural language models for text classification in evidence-based medicine","date":"2020-12-01","arxiv_id":"2012.00584","repositories_listed":0,"syntology":null},{"url":null,"slug":"profile-prediction-an-alignment-based-pre","title":"Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models","date":"2020-12-01","arxiv_id":"2012.00195","repositories_listed":0,"syntology":null},{"url":null,"slug":"prosperamnet-at-fincausal-2020-task-1-2","title":"ProsperAMnet at FinCausal 2020, Task 1 & 2: Modeling causality in financial texts using multi-headed transformers","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-relationship-probing","title":"Self-Supervised Relationship Probing","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-domain-adaptation-for-1","title":"Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"smash-at-semeval-2020-task-7-optimizing-the","title":"Smash at SemEval-2020 Task 7: Optimizing the Hyperparameters of ERNIE 2.0 for Humor Ranking and Rating","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-disfluencies-occur-at-higher","title":"Speech Disfluencies occur at Higher Perplexities","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"surface-realization-using-pretrained-language","title":"Surface Realization Using Pretrained Language Models","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"swagex-at-semeval-2020-task-4-commonsense","title":"SWAGex at SemEval-2020 Task 4: Commonsense Explanation as Next Event Prediction","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"syntax-aware-graph-attention-network-for","title":"Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"textlearner-at-semeval-2020-task-10-a","title":"TextLearner at SemEval-2020 Task 10: A Contextualized Ranking System in Solving Emphasis Selection in Text","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tr-at-semeval-2020-task-4-exploring-the","title":"TR at SemEval-2020 Task 4: Exploring the Limits of Language-model-based Common Sense Validation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"training-linear-finite-state-machines","title":"Training Linear Finite-State Machines","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ui-at-semeval-2020-task-8-text-image-fusion","title":"UI at SemEval-2020 Task 8: Text-Image Fusion for Sentiment Classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-input-and-output-smoothing-in-neural","title":"Unifying Input and Output Smoothing in Neural Machine Translation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-aspect-level-sentiment","title":"Unsupervised Aspect-Level Sentiment Controllable Style Transfer","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/xhate-999-analyzing-and-detecting-abusive","slug":"xhate-999-analyzing-and-detecting-abusive","title":"XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ynu-hpcc-at-semeval-2020-task-10-using-a","title":"YNU-HPCC at SemEval-2020 Task 10: Using a Multi-granularity Ordinal Classification of the BiLSTM Model for Emphasis Selection","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ynutaoxin-at-semeval-2020-task-11","title":"YNUtaoxin at SemEval-2020 Task 11: Identification Fragments of Propaganda Technique by Neural Sequence Labeling Models with Different Tagging Schemes and Pre-trained Language Model","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-accuracy-of-rare-words-for-rnn","title":"Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion","date":"2020-11-30","arxiv_id":"2012.00133","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-homophemes-in-lip-reading-using","title":"Disentangling Homophemes in Lip Reading using Perplexity Analysis","date":"2020-11-28","arxiv_id":"2012.07528","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-query-target-knowledge-discovery","title":"Transformer Query-Target Knowledge Discovery (TEND): Drug Discovery from CORD-19","date":"2020-11-28","arxiv_id":"2012.04682","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-extraction-of-entity-and-relation-with","title":"Joint Extraction of Entity and Relation with Information Redundancy Elimination","date":"2020-11-27","arxiv_id":"2011.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-coding-of-students-writing-via","title":"Automatic coding of students' writing via Contrastive Representation Learning in the Wasserstein space","date":"2020-11-26","arxiv_id":"2011.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"unigram-normalized-perplexity-as-a-language","title":"Unigram-Normalized Perplexity as a Language Model Performance Measure with Different Vocabulary Sizes","date":"2020-11-26","arxiv_id":"2011.13220","repositories_listed":0,"syntology":null},{"url":null,"slug":"adam-a-stochastic-method-with-adaptive-1","title":"Adam$^+$: A Stochastic Method with Adaptive Variance Reduction","date":"2020-11-24","arxiv_id":"2011.11985","repositories_listed":0,"syntology":null},{"url":"/paper/does-bert-understand-sentiment-leveraging","slug":"does-bert-understand-sentiment-leveraging","title":"Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models","date":"2020-11-23","arxiv_id":"2011.11673","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-language-modeling-for-improving","title":"Multi-task Language Modeling for Improving Speech Recognition of Rare Words","date":"2020-11-23","arxiv_id":"2011.11715","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-storytelling-with-large-scale","title":"Collaborative Storytelling with Large-scale Neural Language Models","date":"2020-11-20","arxiv_id":"2011.10208","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-with-cross-modal","title":"Self-Supervised learning with cross-modal transformers for emotion recognition","date":"2020-11-20","arxiv_id":"2011.10652","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-multi-modal-encoder-for-moment","title":"A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus","date":"2020-11-18","arxiv_id":"2011.09046","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictions-for-pre-training-language-models","title":"Predictions For Pre-training Language Models","date":"2020-11-18","arxiv_id":"2011.09031","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascade-rnn-transducer-syllable-based","title":"Cascade RNN-Transducer: Syllable Based Streaming On-device Mandarin Speech Recognition with a Syllable-to-Character Converter","date":"2020-11-17","arxiv_id":"2011.08469","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-and-functional-decomposition-for","title":"Structural and Functional Decomposition for Personality Image Captioning in a Communication Game","date":"2020-11-17","arxiv_id":"2011.08543","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditioned-natural-language-generation-using","title":"Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration","date":"2020-11-14","arxiv_id":"2011.07347","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-value-of-personalized-word","title":"Exploring the Value of Personalized Word Embeddings","date":"2020-11-11","arxiv_id":"2011.06057","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-discrete-energy-based-models-via","title":"Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration","date":"2020-11-10","arxiv_id":"2011.05363","repositories_listed":0,"syntology":null},{"url":null,"slug":"catch-the-tails-of-bert","title":"Positional Artefacts Propagate Through Masked Language Model Embeddings","date":"2020-11-09","arxiv_id":"2011.04393","repositories_listed":0,"syntology":null}],"record_sha256":"d3cddfc0a48da53fe55c5b6554dfe4147ed09347cd5ff745a43de75a2e573936","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}