{"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-modeling/papers/125","list_of":"/task/language-modeling","task":"Language Modeling","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":125,"pages_in_order":142,"rows_per_page":100,"rows":[12401,12500],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling","prev":"/task/language-modeling/papers/124","next":"/task/language-modeling/papers/126","papers":[{"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":"/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":"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},{"url":null,"slug":"improving-commonsense-question-answering-by","title":"Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources","date":"2020-11-05","arxiv_id":"2011.02705","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-is-all-you-need-natural","title":"Language Model is All You Need: Natural Language Understanding as Question Answering","date":"2020-11-05","arxiv_id":"2011.03023","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neuro-symbolic-method-for-solving","title":"A Neuro-Symbolic Method for Solving Differential and Functional Equations","date":"2020-11-04","arxiv_id":"2011.02415","repositories_listed":0,"syntology":null},{"url":null,"slug":"internal-language-model-estimation-for-domain","title":"Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition","date":"2020-11-03","arxiv_id":"2011.01991","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-event-salience-in-narratives-via","title":"Modeling Event Salience in Narratives via Barthes' Cardinal Functions","date":"2020-11-03","arxiv_id":"2011.01785","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-contextual-data","title":"An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution","date":"2020-11-02","arxiv_id":"2011.00948","repositories_listed":0,"syntology":null},{"url":null,"slug":"indolem-and-indobert-a-benchmark-dataset-and","title":"IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP","date":"2020-11-02","arxiv_id":"2011.00677","repositories_listed":0,"syntology":null},{"url":null,"slug":"a3-108-machine-translation-system-for-similar","title":"A3-108 Machine Translation System for Similar Language Translation Shared Task 2020","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-mk-integrating-graph-contextualized","title":"BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/biobertpt-a-portuguese-neural-language-model","slug":"biobertpt-a-portuguese-neural-language-model","title":"BioBERTpt - A Portuguese Neural Language Model for Clinical Named Entity Recognition","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"centering-based-neural-coherence-modeling","title":"Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complexdatalab-at-w-nut-2020-task-2-detecting","title":"ComplexDataLab at W-NUT 2020 Task 2: Detecting Informative COVID-19 Tweets by Attending over Linked Documents","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-the-dots-event-graph-schema","title":"Connecting the Dots: Event Graph Schema Induction with Path Language Modeling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-dependency-parsing-by-pos","title":"Cross-Lingual Dependency Parsing by POS-Guided Word Reordering","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transformers-for-neural","title":"Cross-Lingual Transformers for Neural Automatic Post-Editing","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cxp949-at-wnut-2020-task-2-extracting-1","title":"CXP949 at WNUT-2020 Task 2: Extracting Informative COVID-19 Tweets - RoBERTa Ensembles and The Continued Relevance of Handcrafted Features","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-transfer-learning-for-adverse","title":"Evaluation of Transfer Learning for Adverse Drug Event (ADE) and Medication Entity Extraction","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-clinical-decision-support-from","title":"Explainable Clinical Decision Support from Text","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-study-on-using-pretrained-language","title":"Extended Study on Using Pretrained Language Models and YiSi-1 for Machine Translation Evaluation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fenas-flexible-and-expressive-neural","title":"FENAS: Flexible and Expressive Neural Architecture Search","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-zero-to-hero-on-the-limitations-of-zero-1","title":"From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grammaticality-and-language-modelling","title":"Grammaticality and Language Modelling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gtcom-neural-machine-translation-systems-for-1","title":"GTCOM Neural Machine Translation Systems for WMT20","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hltri-at-w-nut-2020-shared-task-3-covid-19","title":"HLTRI at W-NUT 2020 Shared Task-3: COVID-19 Event Extraction from Twitter Using Multi-Task Hopfield Pooling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-emoji-based-masked-language-models-for","title":"Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"i-d-rather-just-go-to-bed-understanding-1","title":"``I'd rather just go to bed'': Understanding Indirect Answers","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-personal-experience-tweets-of","title":"Identifying Personal Experience Tweets of Medication Effects Using Pre-trained RoBERTa Language Model and Its Updating","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imec-etro-vub-at-w-nut-2020-shared-task-3-a","title":"imec-ETRO-VUB at W-NUT 2020 Shared Task-3: A multilabel BERT-based system for predicting COVID-19 events","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-parallel-data-identification-using","title":"Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-cross-lingual-transfer-with-meta","title":"Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-physical-common-sense-as-knowledge","title":"Learning Physical Common Sense as Knowledge Graph Completion via BERT Data Augmentation and Constrained Tucker Factorization","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"log-linear-reformulation-of-the-noisy-channel","title":"Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-translation-as-language-modeling","title":"Low-Resource Translation as Language Modeling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-translation-reference-less-evaluation","title":"Machine Translation Reference-less Evaluation using YiSi-2 with Bilingual Mappings of Massive Multilingual Language Model","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-local-news-coverage-precise-location","title":"Mapping Local News Coverage: Precise location extraction in textual news content using fine-tuned BERT based language model","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monash-summ-longsumm-20-scisummpip-an","title":"Monash-Summ@LongSumm 20 SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"naver-labs-europes-participation-in-the","title":"Naver Labs Europe’s Participation in the Robustness, Chat, and Biomedical Tasks at WMT 2020","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nict-kyoto-submission-for-the-wmt20-quality","title":"NICT Kyoto Submission for the WMT’20 Quality Estimation Task: Intermediate Training for Domain and Task Adaptation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"njus-submission-to-the-wmt20-qe-shared-task","title":"NJU’s submission to the WMT20 QE Shared Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nlp-pingan-tech-cl-scisumm-2020","title":"NLP-PINGAN-TECH @ CL-SciSumm 2020","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"palm-pre-training-an-autoencoding-1","title":"PALM: Pre-training an Autoencoding\\&Autoregressive Language Model for Context-conditioned Generation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"postech-etris-submission-to-the-wmt2020-ape","title":"POSTECH-ETRI’s Submission to the WMT2020 APE Shared Task: Automatic Post-Editing with Cross-lingual Language Model","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-representation-degeneration","title":"Revisiting Representation Degeneration Problem in Language Modeling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sjtu-nicts-supervised-and-unsupervised-neural","title":"SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sunbear-at-wnut-2020-task-2-improving-bert","title":"SunBear at WNUT-2020 Task 2: Improving BERT-Based Noisy Text Classification with Knowledge of the Data domain","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tesa-a-task-in-entity-semantic-aggregation","title":"TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"test-positive-at-w-nut-2020-shared-task-3-1","title":"TEST_POSITIVE at W-NUT 2020 Shared Task-3: Cross-task modeling","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-amazing-world-of-neural-language","title":"The Amazing World of Neural Language Generation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-university-of-edinburghs-english-tamil","title":"The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tri-train-automatic-pre-fine-tuning-between","title":"Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"truecasing-german-user-generated","title":"Truecasing German user-generated conversational text","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"two-phase-cross-lingual-language-model-fine","title":"Two-Phase Cross-Lingual Language Model Fine-Tuning for Machine Translation Quality Estimation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-neural-transducer-for-large","title":"Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition","date":"2020-10-30","arxiv_id":"2010.16368","repositories_listed":0,"syntology":null},{"url":null,"slug":"slm-learning-a-discourse-language","title":"SLM: Learning a Discourse Language Representation with Sentence Unshuffling","date":"2020-10-30","arxiv_id":"2010.16249","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bert-conditioning-the-language","title":"Contextual BERT: Conditioning the Language Model Using a Global State","date":"2020-10-29","arxiv_id":"2010.15778","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-attentive-fusion-external-language","title":"Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model","date":"2020-10-29","arxiv_id":"2010.15437","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-models-for-improved-visual-captioning","title":"Fusion Models for Improved Visual Captioning","date":"2020-10-28","arxiv_id":"2010.15251","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-in-a-hundred-select-the-best-predicted","title":"One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition","date":"2020-10-28","arxiv_id":"2010.14791","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-decoder-masking-for-transformer","title":"Effective Decoder Masking for Transformer Based End-to-End Speech Recognition","date":"2020-10-27","arxiv_id":"2010.14764","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-training-with-text-data-for-end-to","title":"Multitask Training with Text Data for End-to-End Speech Recognition","date":"2020-10-27","arxiv_id":"2010.14318","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-neural-language-model-fusion-for","title":"Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer","date":"2020-10-26","arxiv_id":"2010.13878","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-task-oriented-dialogue-representation","title":"Probing Task-Oriented Dialogue Representation from Language Models","date":"2020-10-26","arxiv_id":"2010.13912","repositories_listed":0,"syntology":null},{"url":null,"slug":"clplm-character-level-pretrained-language-1","title":"CLPLM: Character Level Pretrained Language Model for Extracting Support Phrases for Sentiment Labels","date":"2020-10-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-decoder-for-neural-machine","title":"Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model","date":"2020-10-24","arxiv_id":"2010.12827","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-mitigating-classification-bias","title":"On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning","date":"2020-10-24","arxiv_id":"2010.12864","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-paraphrase-generation-via","title":"Unsupervised Paraphrasing with Pretrained Language Models","date":"2020-10-24","arxiv_id":"2010.12885","repositories_listed":0,"syntology":null},{"url":null,"slug":"customizing-triggers-with-concealed-data","title":"Concealed Data Poisoning Attacks on NLP Models","date":"2020-10-23","arxiv_id":"2010.12563","repositories_listed":0,"syntology":null},{"url":null,"slug":"dict-mlm-improved-multilingual-pre-training","title":"DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries","date":"2020-10-23","arxiv_id":"2010.12566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-bert-post-pretraining-alignment","title":"Multilingual BERT Post-Pretraining Alignment","date":"2020-10-23","arxiv_id":"2010.12547","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-minimum-word-error-rate-training-of-the","title":"On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer","date":"2020-10-23","arxiv_id":"2010.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-transformer-growth-for-progressive","title":"On the Transformer Growth for Progressive BERT Training","date":"2020-10-23","arxiv_id":"2010.12562","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-model-for-chinese-word","title":"Pre-training with Meta Learning for Chinese Word Segmentation","date":"2020-10-23","arxiv_id":"2010.12272","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-document-representations-using-latent","title":"Robust Document Representations using Latent Topics and Metadata","date":"2020-10-23","arxiv_id":"2010.12681","repositories_listed":0,"syntology":null},{"url":null,"slug":"st-bert-cross-modal-language-model-pre","title":"ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding","date":"2020-10-23","arxiv_id":"2010.12283","repositories_listed":0,"syntology":null}],"record_sha256":"10e2b09617ebbd38baac093df3ff5149ac70078796cc7e5ae1a836da7cb6bcff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}