{"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":"/method/multi-head-attention/papers/182","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":182,"pages_in_order":249,"rows_per_page":100,"rows":[18101,18200],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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":"/method/multi-head-attention","prev":"/method/multi-head-attention/papers/181","next":"/method/multi-head-attention/papers/183","papers":[{"paper":null,"slug":"tervit-an-efficient-ternary-vision","title":"TerViT: An Efficient Ternary Vision Transformer","date":"2022-01-20","arxiv_id":"2201.08050","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-approaches-for-building","slug":"transfer-learning-approaches-for-building","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","date":"2022-01-20","arxiv_id":"2201.08471","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hltcoe/colbert-x"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gap-gen-guided-automatic-python-code","slug":"gap-gen-guided-automatic-python-code","title":"GAP-Gen: Guided Automatic Python Code Generation","date":"2022-01-19","arxiv_id":"2201.08810","n_code_links":1,"syntology":null},{"paper":"/paper/near-optimal-sparse-allreduce-for-distributed","slug":"near-optimal-sparse-allreduce-for-distributed","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","date":"2022-01-19","arxiv_id":"2201.07598","n_code_links":1,"syntology":null},{"paper":"/paper/poseur-direct-human-pose-regression-with","slug":"poseur-direct-human-pose-regression-with","title":"Poseur: Direct Human Pose Regression with Transformers","date":"2022-01-19","arxiv_id":"2201.07412","n_code_links":1,"syntology":null},{"paper":"/paper/q-vit-fully-differentiable-quantization-for","slug":"q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","arxiv_id":"2201.07703","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhexinli/Q-ViT-DeiT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"swin-pose-swin-transformer-based-human-pose","title":"Swin-Pose: Swin Transformer Based Human Pose Estimation","date":"2022-01-19","arxiv_id":"2201.07384","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfuse-a-unified-transformer-based-image","title":"TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning","date":"2022-01-19","arxiv_id":"2201.07451","n_code_links":0,"syntology":null},{"paper":"/paper/coauthor-designing-a-human-ai-collaborative","slug":"coauthor-designing-a-human-ai-collaborative","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","date":"2022-01-18","arxiv_id":"2201.06796","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtrans-spatiotemporal-autoregressive","title":"GTrans: Spatiotemporal Autoregressive Transformer with Graph Embeddings for Nowcasting Extreme Events","date":"2022-01-18","arxiv_id":"2201.06717","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-neural-network-approaches-for","title":"Hierarchical Neural Network Approaches for Long Document Classification","date":"2022-01-18","arxiv_id":"2201.06774","n_code_links":0,"syntology":null},{"paper":"/paper/motion-inbetweening-via-deep-d-interpolator","slug":"motion-inbetweening-via-deep-d-interpolator","title":"Motion Inbetweening via Deep $Δ$-Interpolator","date":"2022-01-18","arxiv_id":"2201.06701","n_code_links":1,"syntology":null},{"paper":null,"slug":"repre-improving-self-supervised-vision","title":"RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training","date":"2022-01-18","arxiv_id":"2201.06857","n_code_links":0,"syntology":null},{"paper":"/paper/resistance-training-using-prior-bias-toward","slug":"resistance-training-using-prior-bias-toward","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","date":"2022-01-18","arxiv_id":"2201.06794","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chch1999/rtpb"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-controllable-protein-design-with","title":"Controllable Protein Design with Language Models","date":"2022-01-18","arxiv_id":"2201.07338","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-vs-albert-explained","title":"BERT vs ALBERT explained","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/continual-transformers-redundancy-free","slug":"continual-transformers-redundancy-free","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","date":"2022-01-17","arxiv_id":"2201.06268","n_code_links":1,"syntology":null},{"paper":null,"slug":"disentangled-latent-transformer-for","title":"Disentangled Latent Transformer for Interpretable Monocular Height Estimation","date":"2022-01-17","arxiv_id":"2201.06357","n_code_links":0,"syntology":null},{"paper":"/paper/korean-specific-dataset-for-table-question","slug":"korean-specific-dataset-for-table-question","title":"Korean-Specific Dataset for Table Question Answering","date":"2022-01-17","arxiv_id":"2201.06223","n_code_links":1,"syntology":null},{"paper":null,"slug":"looking-at-the-performer-from-a-hopfield","title":"Looking at the Performer from a Hopfield Point of View","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/mulve-a-multi-language-vocabulary-evaluation","slug":"mulve-a-multi-language-vocabulary-evaluation","title":"MuLVE, A Multi-Language Vocabulary Evaluation Data Set","date":"2022-01-17","arxiv_id":"2201.06286","n_code_links":0,"syntology":null},{"paper":"/paper/squire-a-sequence-to-sequence-framework-for","slug":"squire-a-sequence-to-sequence-framework-for","title":"SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning","date":"2022-01-17","arxiv_id":"2201.06206","n_code_links":1,"syntology":null},{"paper":"/paper/swinunet3d-a-hierarchical-architecture-for","slug":"swinunet3d-a-hierarchical-architecture-for","title":"SwinUNet3D -- A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers","date":"2022-01-17","arxiv_id":"2201.06390","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bojesomo/Traffic4Cast2021-SwinUNet3D"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unintended-bias-in-language-model","title":"Unintended Bias in Language Model-driven Conversational Recommendation","date":"2022-01-17","arxiv_id":"2201.06224","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-balanced-data-approach-for-evaluating-cross","title":"A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-granularity-opinion-summarization","title":"A Multi-Granularity Opinion Summarization Method","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-pre-trained-language-models-for","title":"A Study of Pre-trained Language Models for Analogy Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-the-attention-abnormality-in","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented-1","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploitation-of-heterogeneous-graph-neural","title":"An Exploitation of Heterogeneous Graph Neural Network for Extractive Long Document Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"autoattention-automatic-attention-head","title":"AutoAttention: Automatic Attention Head Selection Through Differentiable Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-conduct-logical-reasoning-on-the","title":"Can BERT Conduct Logical Reasoning? On the Difficulty of Learning to Reason from Data","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"challenge-for-open-domain-targeted-sentiment","title":"Challenge for open-domain targeted sentiment analysis","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-customize-a-unique","title":"Context-Aware Prompt: Customize A Unique Prompt For Each Input","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"conventional-clustering-based-method-for","title":"Conventional clustering-based method for event detection on social networks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deck-behavioral-tests-to-improve","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-and-conquer-text-semantic-matching","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-berts-learn-to-use-browser-user-interface","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-hierarchical-domain-adaptation-for-1","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-zero-shot-semantic-parsing-with","title":"Efficient Zero-Shot Semantic Parsing with Paraphrasing from Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elastic-weight-consolidation-for-reduction-of","title":"Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ernie-layout-layout-knowledge-enhanced-multi","slug":"ernie-layout-layout-knowledge-enhanced-multi","title":"ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding","date":"2022-01-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"event-detection-via-derangement-reading","title":"Event Detection via Derangement Reading Comprehension","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-adversarial-attacks-on-text-1","title":"Experiments with adversarial attacks on text genres","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-example-selection-for-few-shot-text","title":"Exploring Example Selection for Few-shot Text-to-SQL Semantic Parsing","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-low-resource-transfer-learning","title":"Exploring the Low-Resource Transfer-Learning with mT5 model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extract-select-and-rewrite-a-new-modular","title":"Extract, Select and Rewrite: A New Modular Summarization Method","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fednlp-benchmarking-federated-learning","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-semantic-parsing-with-language-1","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"focus-driven-contrastive-learning-for-medical","title":"Focus-Driven Contrastive Learning for Medical Question Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"global-entity-disambiguation-with-bert","title":"Global Entity Disambiguation with BERT","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformers-are-more-efficient-1","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-the-source-of-vulnerability-in","title":"Identifying the Source of Vulnerability in Fragile Interpretations: A Case Study in Neural Text Classification","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impli-investigatng-nli-models-performance-on","title":"IMPLI: Investigatng NLI Models' Performance on Figurative Language","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-contextual-representation-with","title":"Improving Contextual Representation with Gloss Regularized Pre-training","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-and-explaining-feature-and","title":"Investigating and Explaining Feature and Representation Learning in Translationese Classification","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-saliency-of-sentiment","title":"Investigating the saliency of sentiment expressions in aspect-based sentiment analysis","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kat-a-knowledge-augmented-transformer-for-1","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kd-vlp-improving-end-to-end-vision-and-1","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-for-code-switch-detection-of","title":"Language Models for Code-switch Detection of te reo Māori and English in a Low-resource Setting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-transpile-amr-into-sparql-1","title":"Learning to Transpile AMR into SPARQL","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lope-learnable-sinusoidal-positional-encoding","title":"LoPE: Learnable Sinusoidal Positional Encoding for Improving Document Transformer Model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with-1","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-word-context-biases-in-lexical","title":"Measuring Word-Context Biases in Lexical Semantic Datasets","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/memory-assisted-prompt-editing-to-improve-gpt","slug":"memory-assisted-prompt-editing-to-improve-gpt","title":"Memory-assisted prompt editing to improve GPT-3 after deployment","date":"2022-01-16","arxiv_id":"2201.06009","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["madaan/memprompt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"minimally-supervised-relation-induction-from","title":"Minimally-Supervised Relation Induction from Pre-trained Language Model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-multi-granularity-hierarchical","title":"Modeling Multi-Granularity Hierarchical Features for Relation Extraction","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"must-a-framework-for-training-task-oriented","title":"MUST: A Framework for Training Task-oriented Dialogue Systems with Multiple User SimulaTors","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-deduction-through-search","title":"Natural Language Deduction through Search over Statement Compositions","date":"2022-01-16","arxiv_id":"2201.06028","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-neural-machine-translation-2","title":"Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"patching-leaks-in-the-charformer-for","title":"Patching Leaks in the Charformer for Generative Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pcee-bert-accelerating-bert-inference-via","title":"PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"penguins-dont-fly-reasoning-about-generics","title":"Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-the-linguistic-capacity-of-pre","title":"Probing The Linguistic Capacity of Pre-Trained Vision-Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reframing-human-ai-collaboration-for-1","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-additive-compositionality-and-or-1","title":"Revisiting Additive Compositionality: AND, OR, and NOT Operations with Word Embeddings","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robin-a-novel-online-suicidal-text-corpus-of","title":"Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"roof-bert-divide-understanding-labour-and-1","title":"Roof-BERT: Divide Understanding Labour and Join in Work","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"s5-framework-a-review-of-self-supervised","title":"S5 Framework: A Review of Self-Supervised Shared Semantic Space Optimization for Multimodal Zero-Shot Learning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semattack-natural-textual-attacks-via","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":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,"n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-local-attentions-remain-competitive-1","title":"Simple Local Attentions Remain Competitive for Long-Context Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"surprisingly-simple-adapter-ensembling-for","title":"Surprisingly Simple Adapter Ensembling for Zero-Shot Cross-Lingual Sequence Tagging","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tacl-improving-bert-pre-training-with-token-1","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tapping-bert-for-preposition-sense-1","title":"Tapping BERT for Preposition Sense Disambiguation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"c657b65fcc0422942449d407d88538f953cf68af2c24d7f15c4dab707bacfbb6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}