{"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/146","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":146,"pages_in_order":177,"rows_per_page":100,"rows":[14501,14600],"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/145","next":"/task/language-modelling/papers/147","papers":[{"url":null,"slug":"sustainable-modular-debiasing-of-language","title":"Sustainable Modular Debiasing of Language Models","date":"2021-09-08","arxiv_id":"2109.03646","repositories_listed":0,"syntology":null},{"url":"/paper/generate-rank-a-multi-task-framework-for-math","slug":"generate-rank-a-multi-task-framework-for-math","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","date":"2021-09-07","arxiv_id":"2109.03034","repositories_listed":0,"syntology":null},{"url":null,"slug":"rare-words-degenerate-all-words","title":"Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings","date":"2021-09-07","arxiv_id":"2109.03127","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-attention-module-for-natural","title":"Sequential Attention Module for Natural Language Processing","date":"2021-09-07","arxiv_id":"2109.03009","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-should-evaluate-your-language-model-on","title":"You should evaluate your language model on marginal likelihood over tokenisations","date":"2021-09-06","arxiv_id":"2109.02550","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-lexical-translation","title":"Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT","date":"2021-09-03","arxiv_id":"2109.01396","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-need-to-know-everything-efficiently","title":"No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge","date":"2021-09-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-exploration-in-quality-filtering","title":"An Empirical Exploration in Quality Filtering of Text Data","date":"2021-09-02","arxiv_id":"2109.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"conqx-semantic-expansion-of-spoken-queries","title":"ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation","date":"2021-09-02","arxiv_id":"2109.00729","repositories_listed":0,"syntology":null},{"url":null,"slug":"legalmfit-efficient-short-legal-text","title":"LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training","date":"2021-09-02","arxiv_id":"2109.00993","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-conditionality-for-natural","title":"Multimodal Conditionality for Natural Language Generation","date":"2021-09-02","arxiv_id":"2109.01229","repositories_listed":0,"syntology":null},{"url":null,"slug":"travelbert-pre-training-language-model","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","date":"2021-09-02","arxiv_id":"2109.01048","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-of-modern-pre-trained-language","title":"Behavior of Modern Pre-trained Language Models Using the Example of Probing Tasks","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bpomp-the-benchmark-of-poetic-minimal-pairs","title":"BPoMP: The Benchmark of Poetic Minimal Pairs – Limericks, Rhyme, and Narrative Coherence","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-a-clinical-language-model-for","title":"Developing a Clinical Language Model for Swedish: Continued Pretraining of Generic BERT with In-Domain Data","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-knowledge-help-general-nlu-an-empirical","title":"Does Knowledge Help General NLU? An Empirical Study","date":"2021-09-01","arxiv_id":"2109.00563","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-japanese-electra-model-using","title":"Domain-Specific Japanese ELECTRA Model Using a Small Corpus","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-character-aware-neural-language","title":"Improving Character-Aware Neural Language Model by Warming up Character Encoder under Skip-gram Architecture","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ircologne-at-germeval-2021-toxicity","title":"IRCologne at GermEval 2021: Toxicity Classification","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-asr-with-an-augmented-language","title":"Low-Resource ASR with an Augmented Language Model","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-adversarial-generation-for-neural","title":"Masked Adversarial Generation for Neural Machine Translation","date":"2021-09-01","arxiv_id":"2109.00417","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-borrowing-detection-with-monolingual","title":"Neural Borrowing Detection with Monolingual Lexical Models","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-reducing-repetition-in-abstractive","title":"On Reducing Repetition in Abstractive Summarization","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"split-and-rephrase-in-a-cross-lingual-manner","title":"Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-language-model-for-temporal","title":"Towards a Language Model for Temporal Commonsense Reasoning","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-text-style-transfer-with-content","title":"Unsupervised Text Style Transfer with Content Embeddings","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"watching-a-language-model-learning-chess","title":"Watching a Language Model Learning Chess","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-of-deep-networks-in-nlp-using","title":"Effectiveness of Deep Networks in NLP using BiDAF as an example architecture","date":"2021-08-31","arxiv_id":"2109.00074","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-adversarial-fine-tuning-benefit-bert","title":"How Does Adversarial Fine-Tuning Benefit BERT?","date":"2021-08-31","arxiv_id":"2108.13602","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-data-size-on-automated-essay","title":"The effects of data size on Automated Essay Scoring engines","date":"2021-08-30","arxiv_id":"2108.13275","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-memorization-for-fast-learning","title":"Representation Memorization for Fast Learning New Knowledge without Forgetting","date":"2021-08-28","arxiv_id":"2108.12596","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-retraining-free-speech-recognition","title":"Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching","date":"2021-08-27","arxiv_id":"2109.00921","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-capacity-of-a-large-scale","title":"Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical Errors","date":"2021-08-27","arxiv_id":"2108.12216","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-callsign-recognition-with-air","title":"Improving callsign recognition with air-surveillance data in air-traffic communication","date":"2021-08-27","arxiv_id":"2108.12156","repositories_listed":0,"syntology":null},{"url":null,"slug":"injecting-text-in-self-supervised-speech","title":"Injecting Text in Self-Supervised Speech Pretraining","date":"2021-08-27","arxiv_id":"2108.12226","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-invariant-truecasing-with-a-word-and","title":"Position-Invariant Truecasing with a Word-and-Character Hierarchical Recurrent Neural Network","date":"2021-08-26","arxiv_id":"2108.11943","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-criminal-texts-for-the-polish","title":"Detection of Criminal Texts for the Polish State Border Guard","date":"2021-08-24","arxiv_id":"2108.10580","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-learning-for-fine-grained-entity","title":"Prompt-Learning for Fine-Grained Entity Typing","date":"2021-08-24","arxiv_id":"2108.10604","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-exposure-bias-in-training-recurrent","title":"Reducing Exposure Bias in Training Recurrent Neural Network Transducers","date":"2021-08-24","arxiv_id":"2108.10803","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-the-beast-learning-to-control-neural","title":"Taming the Beast: Learning to Control Neural Conversational Models","date":"2021-08-24","arxiv_id":"2108.10561","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-bert-encoding-and-sentence-level","title":"Using BERT Encoding and Sentence-Level Language Model for Sentence Ordering","date":"2021-08-24","arxiv_id":"2108.10986","repositories_listed":0,"syntology":null},{"url":null,"slug":"uzbert-pretraining-a-bert-model-for-uzbek","title":"UzBERT: pretraining a BERT model for Uzbek","date":"2021-08-22","arxiv_id":"2108.09814","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-multi-object-relationships-for","title":"Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes","date":"2021-08-19","arxiv_id":"2108.08421","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-augmented-relevance-score","title":"Language Model Augmented Relevance Score","date":"2021-08-19","arxiv_id":"2108.08485","repositories_listed":0,"syntology":null},{"url":"/paper/0-8-nyquist-computational-ghost-imaging-via","slug":"0-8-nyquist-computational-ghost-imaging-via","title":"0.8% Nyquist computational ghost imaging via non-experimental deep learning","date":"2021-08-17","arxiv_id":"2108.07673","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-multi-label-prompting-simple-and","title":"Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deduplicating-training-data-makes-language-1","title":"Deduplicating Training Data Makes Language Models Better","date":"2021-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-deep-learning","title":"Scaling Laws for Deep Learning","date":"2021-08-17","arxiv_id":"2108.07686","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-natural-language-processing-for-linkedin-1","title":"Deep Natural Language Processing for LinkedIn Search","date":"2021-08-16","arxiv_id":"2108.13300","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-and-captioning-with-unseen-object","title":"Caption Generation on Scenes with Seen and Unseen Object Categories","date":"2021-08-13","arxiv_id":"2108.06165","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-structured-dynamic-sparse-pre","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","date":"2021-08-13","arxiv_id":"2108.06277","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-relevance-ranking-under-the-pre","title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm","date":"2021-08-12","arxiv_id":"2108.05652","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-based-math-language-model-for","title":"A Transformer-based Math Language Model for Handwritten Math Expression Recognition","date":"2021-08-11","arxiv_id":"2108.05002","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-semantics-from-maintenance-records","title":"Extracting Semantics from Maintenance Records","date":"2021-08-11","arxiv_id":"2108.05454","repositories_listed":0,"syntology":null},{"url":null,"slug":"mounting-video-metadata-on-transformer-based","title":"Mounting Video Metadata on Transformer-based Language Model for Open-ended Video Question Answering","date":"2021-08-11","arxiv_id":"2108.05158","repositories_listed":0,"syntology":null},{"url":null,"slug":"clsebert-contrastive-learning-for-syntax","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","date":"2021-08-10","arxiv_id":"2108.04556","repositories_listed":0,"syntology":null},{"url":null,"slug":"intent5-search-result-diversification-using","title":"IntenT5: Search Result Diversification using Causal Language Models","date":"2021-08-09","arxiv_id":"2108.04026","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-evaluation-in-open-ended-text","title":"Language Model Evaluation in Open-ended Text Generation","date":"2021-08-08","arxiv_id":"2108.03578","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-commonsense-knowledge-on","title":"Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims","date":"2021-08-08","arxiv_id":"2108.03731","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladra-net-locally-aware-dynamic-re-read","title":"LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching","date":"2021-08-06","arxiv_id":"2108.02915","repositories_listed":0,"syntology":null},{"url":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-semantic-regression-for-text","title":"Sentence Semantic Regression for Text Generation","date":"2021-08-06","arxiv_id":"2108.02984","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-language-modeling-1","title":"Towards Zero-shot Language Modeling","date":"2021-08-06","arxiv_id":"2108.03334","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmmformer-efficient-and-flexible-transformer","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","date":"2021-08-05","arxiv_id":"2108.02347","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-harm-in-language-models-with","title":"Mitigating harm in language models with conditional-likelihood filtration","date":"2021-08-04","arxiv_id":"2108.07790","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-differentially-private-bert","title":"Large-Scale Differentially Private BERT","date":"2021-08-03","arxiv_id":"2108.01624","repositories_listed":0,"syntology":null},{"url":null,"slug":"your-fairness-may-vary-group-fairness-of","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","date":"2021-08-03","arxiv_id":"2108.01250","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-my-model-using-the-right-evidence","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","date":"2021-08-02","arxiv_id":"2108.00578","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-sentence-weighting-techniques","title":"A Comparison of Sentence-Weighting Techniques for NMT","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pre-training-strategy-for-zero-resource","title":"A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-targeted-assessment-of-incremental-1","title":"A Targeted Assessment of Incremental Processing in Neural Language Models and Humans","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"and-does-not-mean-or-using-formal-languages","title":"AND does not mean OR: Using Formal Languages to Study Language Models' Representations","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"astartwice-at-semeval-2021-task-5-toxic-span","title":"AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attending-self-attention-a-case-study-of","title":"Attending Self-Attention: A Case Study of Visually Grounded Supervision in Vision-and-Language Transformers","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"best-of-both-worlds-making-high-accuracy-non","title":"Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cambridge-at-semeval-2021-task-2-neural-wic","title":"Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clac-bp-at-semeval-2021-task-8-scibert-plus","title":"CLaC-BP at SemEval-2021 Task 8: SciBERT Plus Rules for MeasEval","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-fast-and-slow-a-case-study-on","title":"Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deepblueai-at-semeval-2021-task-7-detecting","title":"DeepBlueAI at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Stacking Diverse Language Model-Based Methods","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"document-grounded-goal-oriented-dialogue","title":"Document-Grounded Goal-Oriented Dialogue Systems on Pre-Trained Language Model with Diverse Input Representation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-language-generation-with-effective","title":"Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-and-evidence-guided-document-level","title":"Entity and Evidence Guided Document-Level Relation Extraction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-morphological-typology-in-zero","title":"Evaluating morphological typology in zero-shot cross-lingual transfer","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"glossreader-at-semeval-2021-task-2-reading","title":"GlossReader at SemEval-2021 Task 2: Reading Definitions Improves Contextualized Word Embeddings","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"he-is-very-intelligent-she-is-very-beautiful","title":"He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ibm-mnlp-ie-at-case-2021-task-1-multigranular","title":"IBM MNLP IE at CASE 2021 Task 1: Multigranular and Multilingual Event Detection on Protest News","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-low-resource-named-entity-1","title":"Improving Low-Resource Named Entity Recognition via Label-Aware Data Augmentation and Curriculum Denoising","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-yu-xun-lian-yu-yan-mo-xing-de-fan-ti-gu","title":"基于预训练语言模型的繁体古文自动句读研究(Automatic Traditional Ancient Chinese Texts Segmentation and Punctuation Based on Pre-training Language Model)","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kace-generating-knowledge-aware-contrastive","title":"KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lets-be-explicit-about-that-distant","title":"Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-and-improving-bert-s-mathematical-1","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning.","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"medai-at-semeval-2021-task-5-start-to-end","title":"MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-for-few-shot-named-entity","title":"Meta-Learning for Few-Shot Named Entity Recognition","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mulda-a-multilingual-data-augmentation","title":"MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mvp-bert-multi-vocab-pre-training-for-chinese","title":"MVP-BERT: Multi-Vocab Pre-training for Chinese BERT","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre-1","title":"nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"noobs-at-semeval-2021-task-4-masked-language","title":"Noobs at Semeval-2021 Task 4: Masked Language Modeling for abstract answer prediction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ns-hunter-bert-cloze-based-semantic-denoising","title":"NS-Hunter: BERT-Cloze Based Semantic Denoising for Distantly Supervised Relation Classification","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-response-generation-with-tensor","title":"Personalized Response Generation with Tensor Factorization","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/phmospell-phonological-and-morphological","slug":"phmospell-phonological-and-morphological","title":"PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"5ab0513e679763cde2d1817bfacab2c28e2a1867742a35b559f9df0a2f26ca58","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}