{"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/140","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":140,"pages_in_order":177,"rows_per_page":100,"rows":[13901,14000],"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/139","next":"/task/language-modelling/papers/141","papers":[{"url":null,"slug":"probing-phoneme-language-and-speaker","title":"Probing phoneme, language and speaker information in unsupervised speech representations","date":"2022-03-30","arxiv_id":"2203.16193","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-media-scientific-research-achievements","title":"Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Model","date":"2022-03-29","arxiv_id":"2203.15595","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualizing-the-relationship-between-encoded","title":"Visualizing the Relationship Between Encoded Linguistic Information and Task Performance","date":"2022-03-29","arxiv_id":"2203.15860","repositories_listed":0,"syntology":null},{"url":null,"slug":"anna-enhanced-language-representation-for-1","title":"ANNA: Enhanced Language Representation for Question Answering","date":"2022-03-28","arxiv_id":"2203.14507","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-in-context-improving-cosine","title":"Comparing in context: Improving cosine similarity measures with a metric tensor","date":"2022-03-28","arxiv_id":"2203.14996","repositories_listed":0,"syntology":null},{"url":null,"slug":"encbp-a-new-benchmark-dataset-for-finer","title":"EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English","date":"2022-03-28","arxiv_id":"2203.14498","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-roadmap-for-big-model","title":"A Roadmap for Big Model","date":"2022-03-26","arxiv_id":"2203.14101","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-linguistic-steganography-based","title":"Autoregressive Linguistic Steganography Based on BERT and Consistency Coding","date":"2022-03-26","arxiv_id":"2203.13972","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-distributional-distortion-in-1","title":"Evaluating Distributional Distortion in Neural Language Modeling","date":"2022-03-24","arxiv_id":"2203.12788","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-dropping-for-efficient-bert-pretraining","title":"Token Dropping for Efficient BERT Pretraining","date":"2022-03-24","arxiv_id":"2203.13240","repositories_listed":0,"syntology":null},{"url":null,"slug":"linearizing-transformer-with-key-value-memory","title":"Linearizing Transformer with Key-Value Memory","date":"2022-03-23","arxiv_id":"2203.12644","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-pre-trained-model-for","title":"Prompt-based System for Personality and Interpersonal Reactivity Prediction","date":"2022-03-23","arxiv_id":"2203.12481","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-textual-out-of-domain-detection","title":"Towards Textual Out-of-Domain Detection without In-Domain Labels","date":"2022-03-22","arxiv_id":"2203.11396","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlsp-2021-shared-task-vietnamese-machine","title":"VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension","date":"2022-03-22","arxiv_id":"2203.11400","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-speech-recognition-decoding-via","title":"Enhancing Speech Recognition Decoding via Layer Aggregation","date":"2022-03-21","arxiv_id":"2203.11325","repositories_listed":0,"syntology":null},{"url":null,"slug":"immersive-text-game-and-personality","title":"Immersive Text Game and Personality Classification","date":"2022-03-20","arxiv_id":"2203.10621","repositories_listed":0,"syntology":null},{"url":"/paper/histruct-improving-extractive-text-1","slug":"histruct-improving-extractive-text-1","title":"HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information","date":"2022-03-17","arxiv_id":"2203.09629","repositories_listed":0,"syntology":null},{"url":null,"slug":"triangular-transfer-freezing-the-pivot-for","title":"Triangular Transfer: Freezing the Pivot for Triangular Machine Translation","date":"2022-03-17","arxiv_id":"2203.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-ability-of-multilingual-masked","title":"Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure","date":"2022-03-16","arxiv_id":"2203.08430","repositories_listed":0,"syntology":null},{"url":null,"slug":"ta-sbert-token-attention-sentence-bert-for","title":"TA-SBERT: Token Attention Sentence-BERT for Improving Sentence Representation","date":"2022-03-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-text-to-sql-capabilities-of-1","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","date":"2022-03-15","arxiv_id":"2204.00498","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-a-tokenizer-for-free-with-private","title":"Training a Tokenizer for Free with Private Federated Learning","date":"2022-03-15","arxiv_id":"2203.09943","repositories_listed":0,"syntology":null},{"url":null,"slug":"contact-a-dutch-covid-19-adapted-bert-for","title":"CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection","date":"2022-03-14","arxiv_id":"2203.07362","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-language-modeling-with-sparse-all","slug":"efficient-language-modeling-with-sparse-all","title":"Efficient Language Modeling with Sparse all-MLP","date":"2022-03-14","arxiv_id":"2203.06850","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-visual-knowledge-in-language-tasks-1","title":"Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer","date":"2022-03-14","arxiv_id":"2203.07519","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-visual-prompt-temporal-answering","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","date":"2022-03-13","arxiv_id":"2203.06667","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-multimodal-generation-on-clip-via-1","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2022-03-12","arxiv_id":"2203.06386","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-discrete-units-necessary-for-spoken","title":"Are discrete units necessary for Spoken Language Modeling?","date":"2022-03-11","arxiv_id":"2203.05936","repositories_listed":0,"syntology":null},{"url":null,"slug":"compilable-neural-code-generation-with","title":"Compilable Neural Code Generation with Compiler Feedback","date":"2022-03-10","arxiv_id":"2203.05132","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-neural-response-measurements","title":"Connecting Neural Response measurements & Computational Models of language: a non-comprehensive guide","date":"2022-03-10","arxiv_id":"2203.05300","repositories_listed":0,"syntology":null},{"url":null,"slug":"internet-augmented-language-models-through","title":"Internet-augmented language models through few-shot prompting for open-domain question answering","date":"2022-03-10","arxiv_id":"2203.05115","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvp-multimodality-guided-visual-pre-training","title":"MVP: Multimodality-guided Visual Pre-training","date":"2022-03-10","arxiv_id":"2203.05175","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-framework-for-multi-domain-speech","title":"A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling","date":"2022-03-09","arxiv_id":"2203.04767","repositories_listed":0,"syntology":null},{"url":null,"slug":"healthprompt-a-zero-shot-learning-paradigm","title":"HealthPrompt: A Zero-shot Learning Paradigm for Clinical Natural Language Processing","date":"2022-03-09","arxiv_id":"2203.05061","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-driven-negative-sampling","title":"LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings","date":"2022-03-09","arxiv_id":"2203.04703","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-select-large-scale-language-model","title":"Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition","date":"2022-03-09","arxiv_id":"2203.05008","repositories_listed":0,"syntology":null},{"url":null,"slug":"extraction-of-sleep-information-from-clinical","title":"Extraction of Sleep Information from Clinical Notes of Patients with Alzheimer's Disease Using Natural Language Processing","date":"2022-03-08","arxiv_id":"2204.09601","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperpelt-unified-parameter-efficient","title":"HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks","date":"2022-03-08","arxiv_id":"2203.03878","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-preserving-linguistic-steganography","title":"Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding","date":"2022-03-08","arxiv_id":"2203.03795","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-side-are-you-on-insider-outsider","title":"Which side are you on? Insider-Outsider classification in conspiracy-theoretic social media","date":"2022-03-08","arxiv_id":"2203.04356","repositories_listed":0,"syntology":null},{"url":null,"slug":"input-tuning-adapting-unfamiliar-inputs-to","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","date":"2022-03-07","arxiv_id":"2203.03131","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-model-multiple-tasks-pathways-for-natural","title":"SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding","date":"2022-03-07","arxiv_id":"2203.03312","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-pre-trained-bert-for-audio","title":"Leveraging Pre-trained BERT for Audio Captioning","date":"2022-03-06","arxiv_id":"2203.02838","repositories_listed":0,"syntology":null},{"url":null,"slug":"unfreeze-with-care-space-efficient-fine","title":"Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models","date":"2022-03-05","arxiv_id":"2203.02652","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-lexical-hypothesis-identifying","title":"Deep Lexical Hypothesis: Identifying personality structure in natural language","date":"2022-03-04","arxiv_id":"2203.02092","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-neural-framework-for-image-caption","title":"A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism","date":"2022-03-03","arxiv_id":"2203.01594","repositories_listed":0,"syntology":null},{"url":null,"slug":"providing-insights-for-open-response-surveys","title":"Providing Insights for Open-Response Surveys via End-to-End Context-Aware Clustering","date":"2022-03-02","arxiv_id":"2203.01294","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-whole-word-masking-always-better-for-1","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","date":"2022-03-01","arxiv_id":"2203.00286","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-grammars-augmenting-transformer","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","date":"2022-03-01","arxiv_id":"2203.00633","repositories_listed":0,"syntology":null},{"url":null,"slug":"cino-a-chinese-minority-pre-trained-language-1","title":"CINO: A Chinese Minority Pre-trained Language Model","date":"2022-02-28","arxiv_id":"2202.13558","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-based-bidirectional-global-context","title":"Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation","date":"2022-02-28","arxiv_id":"2202.13663","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-text-classification-with-2","title":"Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training","date":"2022-02-28","arxiv_id":"2202.13654","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-natural-language-generation-with-1","title":"Controllable Natural Language Generation with Contrastive Prefixes","date":"2022-02-27","arxiv_id":"2202.13257","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-persian-tokenizers","title":"Evaluating Persian Tokenizers","date":"2022-02-22","arxiv_id":"2202.10879","repositories_listed":0,"syntology":null},{"url":null,"slug":"korean-tokenization-for-beam-search-rescoring","title":"Korean Tokenization for Beam Search Rescoring in Speech Recognition","date":"2022-02-22","arxiv_id":"2203.03583","repositories_listed":0,"syntology":null},{"url":null,"slug":"vu-bert-a-unified-framework-for-visual-dialog","title":"VU-BERT: A Unified framework for Visual Dialog","date":"2022-02-22","arxiv_id":"2202.10787","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-discounting-of-implicit-language","title":"Adaptive Discounting of Implicit Language Models in RNN-Transducers","date":"2022-02-21","arxiv_id":"2203.02317","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylebert-chinese-pretraining-by-font-style","title":"StyleBERT: Chinese pretraining by font style information","date":"2022-02-21","arxiv_id":"2202.09955","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-modeling-for-mitigating-toxicity-in","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","date":"2022-02-19","arxiv_id":"2202.09662","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-freem-to-d-alembert-a-large-corpus-and-a","title":"From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French","date":"2022-02-18","arxiv_id":"2202.09452","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-knowledge-intensive-nlp-with-pre","title":"A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models","date":"2022-02-17","arxiv_id":"2202.08772","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-bert-meets-quantum-temporal-convolution","title":"When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing","date":"2022-02-17","arxiv_id":"2203.03550","repositories_listed":0,"syntology":null},{"url":null,"slug":"capitalization-normalization-for-language","title":"Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical RNN Model","date":"2022-02-16","arxiv_id":"2202.08171","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-transfer-from-large-scale","title":"Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers","date":"2022-02-16","arxiv_id":"2202.07894","repositories_listed":0,"syntology":null},{"url":null,"slug":"xfboost-improving-text-generation-with","title":"XFBoost: Improving Text Generation with Controllable Decoders","date":"2022-02-16","arxiv_id":"2202.08124","repositories_listed":0,"syntology":null},{"url":null,"slug":"misinformation-detection-in-social-media","title":"Misinformation Detection in Social Media Video Posts","date":"2022-02-15","arxiv_id":"2202.07706","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-action-model-acquisition-for","title":"Text-Based Action-Model Acquisition for Planning","date":"2022-02-15","arxiv_id":"2202.08373","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-tuning-tuning-language-models-with-image","title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","date":"2022-02-14","arxiv_id":"2202.06574","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-restoration-in-swedish-through","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","date":"2022-02-14","arxiv_id":"2202.06769","repositories_listed":0,"syntology":null},{"url":null,"slug":"usted-improving-asr-with-a-unified-speech-and","title":"USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder","date":"2022-02-12","arxiv_id":"2202.06045","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-does-it-mean-for-a-language-model-to","title":"What Does it Mean for a Language Model to Preserve Privacy?","date":"2022-02-11","arxiv_id":"2202.05520","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaprompt-adaptive-model-training-for-prompt","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","date":"2022-02-10","arxiv_id":"2202.04824","repositories_listed":0,"syntology":null},{"url":null,"slug":"describing-image-focused-in-cognitive-and","title":"Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs","date":"2022-02-10","arxiv_id":"2202.05331","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-volcspeech-system-for-the-icassp-2022","title":"The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge","date":"2022-02-09","arxiv_id":"2202.04261","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-a-language-model-in-a-kiosk-recommender","title":"Using a Language Model in a Kiosk Recommender System at Fast-Food Restaurants","date":"2022-02-08","arxiv_id":"2202.04145","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-guided-injection-of-conformation-to","title":"Prompt-Guided Injection of Conformation to Pre-trained Protein Model","date":"2022-02-07","arxiv_id":"2202.02944","repositories_listed":0,"syntology":null},{"url":null,"slug":"ethics-rules-of-engagement-and-ai-neural","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","date":"2022-02-05","arxiv_id":"2202.02647","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-scaling-laws-in-nmt-the-effect-of-noise-1","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","date":"2022-02-04","arxiv_id":"2202.01994","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyphonic-pitch-detection-with-convolutional","title":"Polyphonic pitch detection with convolutional recurrent neural networks","date":"2022-02-04","arxiv_id":"2202.02115","repositories_listed":0,"syntology":null},{"url":null,"slug":"mslam-massively-multilingual-joint-pre","title":"mSLAM: Massively multilingual joint pre-training for speech and text","date":"2022-02-03","arxiv_id":"2202.01374","repositories_listed":0,"syntology":null},{"url":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"pop-quiz-can-a-large-language-model-help-with","title":"Pop Quiz! Can a Large Language Model Help With Reverse Engineering?","date":"2022-02-02","arxiv_id":"2202.01142","repositories_listed":0,"syntology":null},{"url":null,"slug":"rescorebert-discriminative-speech-recognition","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","date":"2022-02-02","arxiv_id":"2202.01094","repositories_listed":0,"syntology":null},{"url":null,"slug":"bea-base-a-benchmark-for-asr-of-spontaneous","title":"BEA-Base: A Benchmark for ASR of Spontaneous Hungarian","date":"2022-02-01","arxiv_id":"2202.00601","repositories_listed":0,"syntology":null},{"url":null,"slug":"examining-scaling-and-transfer-of-language-1","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","date":"2022-02-01","arxiv_id":"2202.00528","repositories_listed":0,"syntology":null},{"url":null,"slug":"disaster-tweets-classification-using-bert","title":"Disaster Tweets Classification using BERT-Based Language Model","date":"2022-01-31","arxiv_id":"2202.00795","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-fst-class-language-model-for-end-to","title":"Neural-FST Class Language Model for End-to-End Speech Recognition","date":"2022-01-28","arxiv_id":"2201.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"protum-a-new-method-for-prompt-tuning-based","title":"Protum: A New Method For Prompt Tuning Based on \"[MASK]\"","date":"2022-01-28","arxiv_id":"2201.12109","repositories_listed":0,"syntology":null},{"url":null,"slug":"schema-free-dependency-parsing-via-sequence-1","title":"Schema-Free Dependency Parsing via Sequence Generation","date":"2022-01-28","arxiv_id":"2201.12407","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-assessment-of-the-impact-of-ocr-noise-on","title":"An Assessment of the Impact of OCR Noise on Language Models","date":"2022-01-26","arxiv_id":"2202.00470","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnnfuser-generative-pre-trained-transformer","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","date":"2022-01-26","arxiv_id":"2201.11218","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-decoder-transformer-for-end-to-end","title":"On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR","date":"2022-01-26","arxiv_id":"2201.10792","repositories_listed":0,"syntology":null},{"url":null,"slug":"internal-language-model-estimation-through","title":"Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR","date":"2022-01-26","arxiv_id":"2201.11627","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-domain-semantics-to-the-rescue-zero","title":"Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models","date":"2022-01-25","arxiv_id":"2201.10582","repositories_listed":0,"syntology":null},{"url":null,"slug":"whose-language-counts-as-high-quality","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","date":"2022-01-25","arxiv_id":"2201.10474","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-based-modeling-of-mental-disorders-on","title":"Emotion-based Modeling of Mental Disorders on Social Media","date":"2022-01-24","arxiv_id":"2201.09451","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-memory-augmented-language-models","title":"Relational Memory Augmented Language Models","date":"2022-01-24","arxiv_id":"2201.09680","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-and-diverse-arabic-corpus-for","title":"A Large and Diverse Arabic Corpus for Language Modeling","date":"2022-01-23","arxiv_id":"2201.09227","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-application-of-pseudo-log-likelihoods-to","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","date":"2022-01-23","arxiv_id":"2201.09377","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-word-segmentation-with-heterogeneous","title":"Chinese Word Segmentation with Heterogeneous Graph Neural Network","date":"2022-01-22","arxiv_id":"2201.08975","repositories_listed":0,"syntology":null}],"record_sha256":"37868df80e3b8ec1b8caf27dee346c164ef7a76d43249cdceb7f20180802be19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}