{"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/141","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":141,"pages_in_order":177,"rows_per_page":100,"rows":[14001,14100],"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/140","next":"/task/language-modelling/papers/142","papers":[{"url":null,"slug":"identifying-adversarial-attacks-on-text","title":"Identifying Adversarial Attacks on Text Classifiers","date":"2022-01-21","arxiv_id":"2201.08555","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearest-class-center-simplification-through","title":"Nearest Class-Center Simplification through Intermediate Layers","date":"2022-01-21","arxiv_id":"2201.08924","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-style-transfer-for-bias-mitigation-using","title":"Text Style Transfer for Bias Mitigation using Masked Language Modeling","date":"2022-01-21","arxiv_id":"2201.08643","repositories_listed":0,"syntology":null},{"url":null,"slug":"astbert-enabling-language-model-for-code","title":"AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees","date":"2022-01-20","arxiv_id":"2201.07984","repositories_listed":0,"syntology":null},{"url":null,"slug":"tourbert-a-pretrained-language-model-for-the","title":"TourBERT: A pretrained language model for the tourism industry","date":"2022-01-19","arxiv_id":"2201.07449","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-dive-into-cocon-a-self-supervised","title":"Deep dive into CoCon - A Self Supervised approach for Controlled Text Generation","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pplm-revisited-steering-and-beaming-a","title":"PPLM Revisited: Steering and Beaming a Lumbering Mammoth to Control Text Generation","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unintended-bias-in-language-model","title":"Unintended Bias in Language Model-driven Conversational Recommendation","date":"2022-01-17","arxiv_id":"2201.06224","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-masked-segmental-language-model-for-1","title":"A Masked Segmental Language Model for Unsupervised Natural Language Segmentation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-softtriple-loss-for-supervised-1","title":"Applying SoftTriple Loss for Supervised Language Model Fine Tuning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-character-are-subwords-good-enough","title":"Breaking Character: Are Subwords Good Enough for MRLs After All?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-the-gap-between-cv-and-nlp-a-gradient-1","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-distillation-for-language-models-1","title":"Causal Distillation for Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-language-model-for-zero-shot","title":"Causal Language Model for Zero-shot Constrained Keyphrase Generation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cl-rekd-cross-lingual-knowledge-distillation","title":"CL-ReKD: Cross-lingual Knowledge Distillation for Multilingual Retrieval Question Answering","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"codebpe-investigating-subtokenization-options","title":"CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-knowledge-transfer-for-pre","title":"Commonsense Knowledge Transfer for Pre-trained Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-speaker-identification-from","title":"Cross-Lingual Speaker Identification from Weak Local Evidence","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"curriculum-a-broad-coverage-benchmark-for","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-biomedical-factoid","title":"Data Augmentation for Biomedical Factoid Question Answering","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-continuous-prompt-for-contrastive","title":"Deep Continuous Prompt for Contrastive Learning of Sentence Embeddings","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disaggregating-hops-can-we-guide-a-multi-hop","title":"Disaggregating Hops: Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at each Hop?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-aware-prompt-design-for-text-1","title":"Discourse-Aware Prompt Design for Text Generation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"docmt5-document-level-pre-training-of","title":"DOCmT5: Document-Level Pre-training of Multilingual Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dont-forget-about-pronouns-removing-gender","title":"Don’t Forget About Pronouns: Removing Gender Bias in Language Models without Losing Factual Gender Information","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-hierarchical-domain-adaptation-for-1","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-machine-translation-domain","title":"Efficient Machine Translation Domain Adaptation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eici-a-new-method-of-dynamic-embedding","title":"EiCi: A New Method of Dynamic Embedding Incorporating Contextual Information in Chinese NER","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exposing-the-limits-of-video-text-models","title":"Exposing the Limits of Video-Text Models through Contrast Sets","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feasibility-of-bert-embeddings-for-domain","title":"Feasibility of BERT Embeddings For Domain-Specific Knowledge Mining","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-strategies-for-domain-specific","title":"Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hardness-masking-via-auto-regressive-language","title":"Hardness Masking via Auto-Regressive Language Model","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-transformers-are-more-efficient-1","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-qa-models-combine-knowledge-from-lm","title":"How do QA models combine knowledge from LM and 100 passages?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-coherence-of-language-model","title":"Improving Coherence of Language Model Generation with Latent Semantic State","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-conversational-recommendation-2","title":"Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-reinforced-user-simulator-and-task","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-grounded-dialogue-generation-with-a-1","title":"Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lacuna-reconstruction-self-supervised-pre-1","title":"Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cross-lingual-ir-from-an-english-1","title":"Learning Cross-Lingual IR from an English Retriever","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-retrieve-prompts-for-in-context-1","title":"Learning To Retrieve Prompts for In-Context Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-style-transfer-via-domain","title":"Low Resource Style Transfer via Domain Adaptive Meta Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"metaicl-learning-to-learn-in-context-1","title":"MetaICL: Learning to Learn In Context","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"minimally-supervised-relation-induction-from","title":"Minimally-Supervised Relation Induction from Pre-trained Language Model","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mix-and-match-learning-free-controllable-text-1","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-pre-training-for-math","title":"Multi-Stage Pre-Training for Math-Understanding: $\\mu^2$(AL)BERT","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mwp-bert-numeracy-augmented-pre-training-for","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"my-stance-decides-my-language-modeling-of","title":"\"my stance decides my language\": Modeling of Framing and Political Stance in News Media","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-measuring-social-biases-in-prompt-based","title":"On Measuring Social Biases in Prompt-Based Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pneg-prompt-based-negative-response","title":"PNEG: Prompt-based Negative Response Generation for Robust Response Selection Model","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ppl-mcts-constrained-textual-generation","title":"PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"processbert-towards-equivalence-judgment-of","title":"ProcessBERT: Towards Equivalence Judgment of Variable Definitions among Multiple Engineering Documents","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-class-semantic-matching-for-semi","title":"Progressive Class Semantic Matching for Semi-supervised Text Classification","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-adaptability-in-pre-trained-1","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-conversational-1","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-for-resource","title":"Representation Learning for Resource-Constrained Keyphrase Generation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-style-transformer-by-energy-based","title":"Rethinking Style Transformer by Energy-based Interpretation: Adversarial Unsupervised Style Transfer using Pretrained Model","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-visual-facts-for-few-shot-visual","title":"Retrieving Visual Facts For Few-Shot Visual Question Answering","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seq-gan-bert-sequence-generative-adversarial","title":"Seq-GAN-BERT：Sequence Generative Adversarial Learning for Low-resource Name Entity Recognition","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-clustering-in-textual-dialogue-with","title":"Speaker Clustering in Textual Dialogue with Utterance Correlation and Cross-corpus Dialogue Act Supervision","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stt-soft-template-tuning-for-few-shot","title":"STT: Soft Template Tuning for Few-Shot Learning","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-interactive-language-modeling-1","title":"Towards Interactive Language Modeling","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-knowledge-from-structure-aware","title":"Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ubert-a-novel-language-model-for-synonymy","title":"UBERT: A Novel Language Model for Synonymy Prediction at Scale in the UMLS Metathesaurus","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"when-does-syntax-mediate-neural-language","title":"When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"when-more-is-not-necessary-better","title":"When More is not Necessary Better: Multilingual Auxiliary Tasks for Zero-Shot Cross-Lingual Transfer of Hate Speech Detection Models","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-multi-task-learning-method-for","title":"A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognition","date":"2022-01-15","arxiv_id":"2201.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-learning-for-few-shot-dialogue-state","title":"A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking","date":"2022-01-15","arxiv_id":"2201.05780","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-a-generic-sequence-to-sequence-model","title":"Applying a Generic Sequence-to-Sequence Model for Simple and Effective Keyphrase Generation","date":"2022-01-14","arxiv_id":"2201.05302","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dark-side-of-the-language-pre-trained-1","title":"The Dark Side of the Language: Pre-trained Transformers in the DarkNet","date":"2022-01-14","arxiv_id":"2201.05613","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni-eden-universal-encoder-decoder-network-by","title":"Uni-EDEN: Universal Encoder-Decoder Network by Multi-Granular Vision-Language Pre-training","date":"2022-01-11","arxiv_id":"2201.04026","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-modeling-the-programming-world-with","title":"Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning","date":"2022-01-10","arxiv_id":"2201.03346","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-automatic-scoring-of-handwritten","title":"Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests","date":"2022-01-10","arxiv_id":"2201.03215","repositories_listed":0,"syntology":null},{"url":"/paper/a-transfer-learning-pipeline-for-educational","slug":"a-transfer-learning-pipeline-for-educational","title":"A Transfer Learning Pipeline for Educational Resource Discovery with Application in Leading Paragraph Generation","date":"2022-01-07","arxiv_id":"2201.02312","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switching-text-augmentation-for","title":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","date":"2022-01-07","arxiv_id":"2201.02550","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-lens-on-cognition-study-of","title":"Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow","date":"2022-01-07","arxiv_id":"2201.02662","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-analysis-of-art-proxy-learning-of","title":"Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models","date":"2022-01-05","arxiv_id":"2201.01819","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-attention-ai-to-translate-low","title":"Interactive Attention AI to translate low light photos to captions for night scene understanding in women safety","date":"2022-01-04","arxiv_id":"2201.00969","repositories_listed":0,"syntology":null},{"url":null,"slug":"submix-practical-private-prediction-for-large-1","title":"Submix: Practical Private Prediction for Large-Scale Language Models","date":"2022-01-04","arxiv_id":"2201.00971","repositories_listed":0,"syntology":null},{"url":null,"slug":"technology-mapping-using-webai-the-case-of-3d","title":"Technology Mapping Using WebAI: The Case of 3D Printing","date":"2022-01-04","arxiv_id":"2201.01125","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-controllable-variational","title":"Rethinking Controllable Variational Autoencoders","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"textrgnn-residual-graph-neural-networks-for","title":"TextRGNN: Residual Graph Neural Networks for Text Classification","date":"2021-12-30","arxiv_id":"2112.15060","repositories_listed":0,"syntology":null},{"url":null,"slug":"secondary-use-of-clinical-problem-list","title":"Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment","date":"2021-12-27","arxiv_id":"2112.13756","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-roberta-s-mood-the-role-of","title":"Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment","date":"2021-12-27","arxiv_id":"2112.13795","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-dialect-arabic-speech-recognition","title":"Multi-Dialect Arabic Speech Recognition","date":"2021-12-25","arxiv_id":"2112.14678","repositories_listed":0,"syntology":null},{"url":null,"slug":"counterfactual-memorization-in-neural","title":"Counterfactual Memorization in Neural Language Models","date":"2021-12-24","arxiv_id":"2112.12938","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-patient-friendly-clinical-notes","title":"Towards more patient friendly clinical notes through language models and ontologies","date":"2021-12-23","arxiv_id":"2112.12672","repositories_listed":0,"syntology":null},{"url":null,"slug":"diformer-directional-transformer-for-neural","title":"Diformer: Directional Transformer for Neural Machine Translation","date":"2021-12-22","arxiv_id":"2112.11632","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-importance-of-the-current-input-in-1","title":"The Importance of the Current Input in Sequence Modeling","date":"2021-12-22","arxiv_id":"2112.11776","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-large-scale-language-modeling-with","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","date":"2021-12-20","arxiv_id":"2112.10684","repositories_listed":0,"syntology":null},{"url":null,"slug":"spiral-language-modeling","title":"Spiral Language Modeling","date":"2021-12-20","arxiv_id":"2112.10543","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-knowledge-in-end-to-end-automatic","title":"Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching","date":"2021-12-19","arxiv_id":"2112.10202","repositories_listed":0,"syntology":null},{"url":null,"slug":"lerna-transformer-architectures-for","title":"Lerna: Transformer Architectures for Configuring Error Correction Tools for Short- and Long-Read Genome Sequencing","date":"2021-12-19","arxiv_id":"2112.10068","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-learning-with-knowledge-graphs-a","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","date":"2021-12-18","arxiv_id":"2112.10006","repositories_listed":0,"syntology":null},{"url":null,"slug":"autographex-zero-shot-biomedical-definition","title":"AutoGraphex: Zero-shot Biomedical Definition Generation with Automatic Prompting","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pretrained-language-models-are-all-you-need","title":"Pretrained Language Models Are All You Need For Text-to-SQL Schema Linking","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/docmt5-document-level-pretraining-of","slug":"docmt5-document-level-pretraining-of","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","date":"2021-12-16","arxiv_id":"2112.08709","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-pre-training-induce-systematic-inference","title":"Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge","date":"2021-12-16","arxiv_id":"2112.08583","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-prompts-towards-memory-and-compute","title":"Prompt Tuning GPT-2 language model for parameter-efficient domain adaptation of ASR systems","date":"2021-12-16","arxiv_id":"2112.08718","repositories_listed":0,"syntology":null}],"record_sha256":"d58dd9b82edfcab3f64ea99e1b42d87979e3d6f93d725ff3300c0a2106d17da5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}