{"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/attention/papers/258","list_of":"/method/attention","method":"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":258,"pages_in_order":316,"rows_per_page":100,"rows":[25701,25800],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/257","next":"/method/attention/papers/259","papers":[{"paper":null,"slug":"slam-a-unified-encoder-for-speech-and","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","date":"2021-10-20","arxiv_id":"2110.10329","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-and-reliable-iris","title":"Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning","date":"2021-10-20","arxiv_id":"2110.10334","n_code_links":0,"syntology":null},{"paper":null,"slug":"vldeformer-learning-visual-semantic","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","date":"2021-10-20","arxiv_id":"2110.11338","n_code_links":0,"syntology":null},{"paper":"/paper/a-picture-is-worth-a-thousand-words-a-unified","slug":"a-picture-is-worth-a-thousand-words-a-unified","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","date":"2021-10-19","arxiv_id":"2110.09756","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-framework-of-transformer-by","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","date":"2021-10-19","arxiv_id":"2110.10030","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilateral-vit-for-robust-fovea-localization","title":"Bilateral-ViT for Robust Fovea Localization","date":"2021-10-19","arxiv_id":"2110.09860","n_code_links":0,"syntology":null},{"paper":null,"slug":"detectornet-transformer-enhanced-spatial","title":"DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction","date":"2021-10-19","arxiv_id":"2111.00869","n_code_links":0,"syntology":null},{"paper":"/paper/ensemble-albert-on-squad-2-0","slug":"ensemble-albert-on-squad-2-0","title":"Ensemble ALBERT on SQuAD 2.0","date":"2021-10-19","arxiv_id":"2110.09665","n_code_links":1,"syntology":null},{"paper":"/paper/generating-symbolic-reasoning-problems-with-1","slug":"generating-symbolic-reasoning-problems-with-1","title":"Generating Symbolic Reasoning Problems with Transformer GANs","date":"2021-10-19","arxiv_id":"2110.10054","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["reactive-systems/TGAN-SR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"inductive-biases-and-variable-creation-in-1","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","date":"2021-10-19","arxiv_id":"2110.10090","n_code_links":0,"syntology":null},{"paper":"/paper/permutation-invariant-graph-to-sequence-model-1","slug":"permutation-invariant-graph-to-sequence-model-1","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","date":"2021-10-19","arxiv_id":"2110.09681","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["coleygroup/graph2smiles"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"risks-of-ai-foundation-models-in-education","title":"Risks of AI Foundation Models in Education","date":"2021-10-19","arxiv_id":"2110.10024","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-temporal-transformer-for-3d-point","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","date":"2021-10-19","arxiv_id":"2110.09783","n_code_links":0,"syntology":null},{"paper":"/paper/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["YuanGongND/ssast"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/unifying-multimodal-transformer-for-bi","slug":"unifying-multimodal-transformer-for-bi","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","date":"2021-10-19","arxiv_id":"2110.09753","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["researchmm/generate-it"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-data-bootstrapping-recipe-for-low-resource","title":"A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification","date":"2021-10-18","arxiv_id":"2110.09570","n_code_links":0,"syntology":null},{"paper":null,"slug":"bermo-what-can-bert-learn-from-elmo-1","title":"BERMo: What can BERT learn from ELMo?","date":"2021-10-18","arxiv_id":"2110.15802","n_code_links":0,"syntology":null},{"paper":null,"slug":"ceasing-hate-withmoh-hate-speech-detection-in","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","date":"2021-10-18","arxiv_id":"2110.09393","n_code_links":0,"syntology":null},{"paper":"/paper/compositional-attention-disentangling-search-1","slug":"compositional-attention-disentangling-search-1","title":"Compositional Attention: Disentangling Search and Retrieval","date":"2021-10-18","arxiv_id":"2110.09419","n_code_links":3,"syntology":null},{"paper":null,"slug":"contextual-hate-speech-detection-in-code","title":"Contextual Hate Speech Detection in Code Mixed Text using Transformer Based Approaches","date":"2021-10-18","arxiv_id":"2110.09338","n_code_links":0,"syntology":null},{"paper":"/paper/hrformer-high-resolution-transformer-for","slug":"hrformer-high-resolution-transformer-for","title":"HRFormer: High-Resolution Transformer for Dense Prediction","date":"2021-10-18","arxiv_id":"2110.09408","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["HRNet/HRFormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/memo-test-time-robustness-via-adaptation-and","slug":"memo-test-time-robustness-via-adaptation-and","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","date":"2021-10-18","arxiv_id":"2110.09506","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":3,"n_instrument":11,"unverified":4,"pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhangmarvin/memo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/sentimentarcs-a-novel-method-for-self","slug":"sentimentarcs-a-novel-method-for-self","title":"SentimentArcs: A Novel Method for Self-Supervised Sentiment Analysis of Time Series Shows SOTA Transformers Can Struggle Finding Narrative Arcs","date":"2021-10-18","arxiv_id":"2110.09454","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["jon-chun/sentimentarcs_notebooks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/sequential-modeling-with-multiple-attributes","slug":"sequential-modeling-with-multiple-attributes","title":"Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce","date":"2021-10-18","arxiv_id":"2110.11072","n_code_links":1,"syntology":null},{"paper":"/paper/tldr-twin-learning-for-dimensionality-1","slug":"tldr-twin-learning-for-dimensionality-1","title":"TLDR: Twin Learning for Dimensionality Reduction","date":"2021-10-18","arxiv_id":"2110.09455","n_code_links":1,"syntology":null},{"paper":null,"slug":"virapart-a-text-refinement-framework-for-asr","title":"ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian","date":"2021-10-18","arxiv_id":"2110.09086","n_code_links":0,"syntology":null},{"paper":"/paper/3d-retr-end-to-end-single-and-multi-view-3d","slug":"3d-retr-end-to-end-single-and-multi-view-3d","title":"3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers","date":"2021-10-17","arxiv_id":"2110.08861","n_code_links":1,"syntology":null},{"paper":null,"slug":"cae-transformer-transformer-based-model-to","title":"CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans","date":"2021-10-17","arxiv_id":"2110.08721","n_code_links":0,"syntology":null},{"paper":"/paper/illiterate-dall-cdot-e-learns-to-compose-1","slug":"illiterate-dall-cdot-e-learns-to-compose-1","title":"Illiterate DALL-E Learns to Compose","date":"2021-10-17","arxiv_id":"2110.11405","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["singhgautam/slate"],"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":"reminding-the-incremental-language-model-via","title":"Reminding the Incremental Language Model via Data-Free Self-Distillation","date":"2021-10-17","arxiv_id":"2110.08745","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-transformer-pyramid-networks-for-real","slug":"siamese-transformer-pyramid-networks-for-real","title":"Siamese Transformer Pyramid Networks for Real-Time UAV Tracking","date":"2021-10-17","arxiv_id":"2110.08822","n_code_links":1,"syntology":null},{"paper":"/paper/taming-visually-guided-sound-generation","slug":"taming-visually-guided-sound-generation","title":"Taming Visually Guided Sound Generation","date":"2021-10-17","arxiv_id":"2110.08791","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["v-iashin/SpecVQGAN"],"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":["listed","official"]}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-short-study-on-compressing-decoder-based","title":"A Short Study on Compressing Decoder-Based Language Models","date":"2021-10-16","arxiv_id":"2110.08460","n_code_links":0,"syntology":null},{"paper":null,"slug":"alleviating-the-inequality-of-attention-heads-1","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/asformer-transformer-for-action-segmentation","slug":"asformer-transformer-for-action-segmentation","title":"ASFormer: Transformer for Action Segmentation","date":"2021-10-16","arxiv_id":"2110.08568","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chinayi/asformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"attention-temperature-matters-in-abstractive-1","title":"Attention Temperature Matters in Abstractive Summarization Distillation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bitfit-simple-parameter-efficient-fine-tuning-1","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-detection-in-chest-x-ray-images-1","title":"COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformer","date":"2021-10-16","arxiv_id":"2110.08427","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-flip-reasoning-in-multiparty","title":"Emotion Flip Reasoning in Multiparty Conversations","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-style-transfer-with-a-specified","title":"Emotion Style Transfer with a Specified Intensity Using Deep Reinforcement Learning","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enct5-fine-tuning-t5-encoder-for-non","slug":"enct5-fine-tuning-t5-encoder-for-non","title":"EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models","date":"2021-10-16","arxiv_id":"2110.08426","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-networks-for-long","title":"Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","n_code_links":1,"syntology":null},{"paper":null,"slug":"impli-investigating-nli-models-performance-on","title":"IMPLI: Investigating NLI Models' Performance on Figurative Language","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-compositional-generalization-with","slug":"improving-compositional-generalization-with","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","date":"2021-10-16","arxiv_id":"2110.08467","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-inheritance-for-pre-trained-1","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-rich-representation-of-keyphrases","title":"Learning Rich Representation of Keyphrases from Text","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-acquire-knowledge-from-a-search","title":"Learning to Acquire Knowledge from a Search Engine for Dialogue Response Generation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"models-in-a-spelling-bee-language-models-1","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ode-transformer-an-ordinary-differential-1","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/old-bert-new-tricks-artificial-language-1","slug":"old-bert-new-tricks-artificial-language-1","title":"Old BERT, New Tricks: Artificial Language Learning for Pre-Trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-current-state-of-reproducibility-and","title":"On the current state of reproducibility and reporting of uncertainty for Aspect-based Sentiment Analysis","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-the-robustness-of-reading-comprehension","slug":"on-the-robustness-of-reading-comprehension","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-10-16","arxiv_id":"2110.08555","n_code_links":1,"syntology":null},{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/prix-lm-pretraining-for-multilingual","slug":"prix-lm-pretraining-for-multilingual","title":"Prix-LM: Pretraining for Multilingual Knowledge Base Construction","date":"2021-10-16","arxiv_id":"2110.08443","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-search-as-extractive-paraphrase-span","title":"Semantic Search as Extractive Paraphrase Span Detection","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-improves","title":"Sharpness-Aware Minimization Improves Language Model Generalization","date":"2021-10-16","arxiv_id":"2110.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"should-we-trust-this-summary-bayesian","title":"Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spellm-augmenting-chinese-spell-check-using","title":"SpelLM: Augmenting Chinese Spell Check Using Input Salience","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-10-16","arxiv_id":"2110.08525","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-with-a-mixture-of-gaussian-keys-1","slug":"transformer-with-a-mixture-of-gaussian-keys-1","title":"Improving Transformers with Probabilistic Attention Keys","date":"2021-10-16","arxiv_id":"2110.08678","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["minhtannguyen/transformer-mgk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wechsel-effective-initialization-of-subword","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-do-compressed-large-language-models","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","date":"2021-10-16","arxiv_id":"2110.08419","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-cnns-with-transformer-for","title":"Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining","date":"2021-10-15","arxiv_id":"2110.07919","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-gender-bias-in-transformer-based","title":"Detecting Gender Bias in Transformer-based Models: A Case Study on BERT","date":"2021-10-15","arxiv_id":"2110.15733","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-faithfulness-of-importance","slug":"evaluating-the-faithfulness-of-importance","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","date":"2021-10-15","arxiv_id":"2110.08412","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AndreasMadsen/nlp-roar-interpretability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-natural-language-adversarial-1","title":"Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm","date":"2021-10-15","arxiv_id":"2110.08036","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-curriculum-learning-for-amr","slug":"hierarchical-curriculum-learning-for-amr","title":"Hierarchical Curriculum Learning for AMR Parsing","date":"2021-10-15","arxiv_id":"2110.07855","n_code_links":1,"syntology":null},{"paper":null,"slug":"intent-based-product-collections-for-e","title":"Intent-based Product Collections for E-commerce using Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08241","n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","n_code_links":0,"syntology":null},{"paper":"/paper/on-learning-the-transformer-kernel-1","slug":"on-learning-the-transformer-kernel-1","title":"On Learning the Transformer Kernel","date":"2021-10-15","arxiv_id":"2110.08323","n_code_links":1,"syntology":null},{"paper":"/paper/probing-as-quantifying-the-inductive-bias-of","slug":"probing-as-quantifying-the-inductive-bias-of","title":"Probing as Quantifying Inductive Bias","date":"2021-10-15","arxiv_id":"2110.08388","n_code_links":1,"syntology":null},{"paper":null,"slug":"streamult-streaming-multimodal-transformer","title":"StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data","date":"2021-10-15","arxiv_id":"2110.08021","n_code_links":0,"syntology":null},{"paper":"/paper/tracing-origins-coref-aware-machine-reading","slug":"tracing-origins-coref-aware-machine-reading","title":"Tracing Origins: Coreference-aware Machine Reading Comprehension","date":"2021-10-15","arxiv_id":"2110.07961","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-combating-hype-proceed-with-caution","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","date":"2021-10-15","arxiv_id":"2110.08300","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-strong-and-robust-baseline-for","slug":"a-simple-strong-and-robust-baseline-for","title":"PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction","date":"2021-10-14","arxiv_id":"2110.07415","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2bert-towards-reusable-pretrained","title":"bert2BERT: Towards Reusable Pretrained Language Models","date":"2021-10-14","arxiv_id":"2110.07143","n_code_links":0,"syntology":null},{"paper":"/paper/bi-rads-bert-using-section-tokenization-to","slug":"bi-rads-bert-using-section-tokenization-to","title":"BI-RADS BERT & Using Section Segmentation to Understand Radiology Reports","date":"2021-10-14","arxiv_id":"2110.07552","n_code_links":1,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models","slug":"building-chinese-biomedical-language-models","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-10-14","arxiv_id":"2110.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-transformers-perform-below-chance-on","title":"Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans","date":"2021-10-14","arxiv_id":"2110.07240","n_code_links":0,"syntology":null},{"paper":null,"slug":"causally-estimating-the-sensitivity-of-neural-1","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-10-14","arxiv_id":"2110.07159","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-gloss-augmentation-for-improving-word","title":"Context-gloss Augmentation for Improving Word Sense Disambiguation","date":"2021-10-14","arxiv_id":"2110.07174","n_code_links":0,"syntology":null},{"paper":"/paper/delphi-towards-machine-ethics-and-norms","slug":"delphi-towards-machine-ethics-and-norms","title":"Can Machines Learn Morality? The Delphi Experiment","date":"2021-10-14","arxiv_id":"2110.07574","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-off-the-shelf-machine-listening","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","date":"2021-10-14","arxiv_id":"2110.07410","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolutionary-trajectory-and-origin-of-sars","title":"Integrating Fréchet distance and AI reveals the evolutionary trajectory and origin of SARS-CoV-2","date":"2021-10-14","arxiv_id":"2110.07696","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-timbre-disentanglement-in-non","title":"Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech","date":"2021-10-14","arxiv_id":"2110.07192","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-introductions-in-podcast-episodes","slug":"identifying-introductions-in-podcast-episodes","title":"Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts","date":"2021-10-14","arxiv_id":"2110.07096","n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-drug-target-interaction-prediction","title":"Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer","date":"2021-10-14","arxiv_id":"2110.07347","n_code_links":0,"syntology":null},{"paper":"/paper/lfpt5-a-unified-framework-for-lifelong-few-1","slug":"lfpt5-a-unified-framework-for-lifelong-few-1","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","date":"2021-10-14","arxiv_id":"2110.07298","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["qcwthu/lifelong-fewshot-language-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mofe-mixture-of-factual-experts-for-1","title":"CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization","date":"2021-10-14","arxiv_id":"2110.07166","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-translation-with-layer","slug":"non-autoregressive-translation-with-layer","title":"Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision","date":"2021-10-14","arxiv_id":"2110.07515","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chenyangh/dslp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/p-adapters-robustly-extracting-factual-1","slug":"p-adapters-robustly-extracting-factual-1","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","date":"2021-10-14","arxiv_id":"2110.07280","n_code_links":1,"syntology":null},{"paper":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","n_code_links":6,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["microsoft/speecht5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/sub-word-level-lip-reading-with-visual","slug":"sub-word-level-lip-reading-with-visual","title":"Sub-word Level Lip Reading With Visual Attention","date":"2021-10-14","arxiv_id":"2110.07603","n_code_links":0,"syntology":null},{"paper":"/paper/symbolic-knowledge-distillation-from-general","slug":"symbolic-knowledge-distillation-from-general","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","date":"2021-10-14","arxiv_id":"2110.07178","n_code_links":1,"syntology":null},{"paper":"/paper/the-neural-data-router-adaptive-control-flow","slug":"the-neural-data-router-adaptive-control-flow","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-10-14","arxiv_id":"2110.07732","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["robertcsordas/ndr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}}],"record_sha256":"383bcf7e9cc3b3b2b82e3c4774bc8a79d958eb122a530f1bf41f06d6eebb4743","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}