{"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/266","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":266,"pages_in_order":316,"rows_per_page":100,"rows":[26501,26600],"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/265","next":"/method/attention/papers/267","papers":[{"paper":"/paper/understand-me-if-you-refer-to-aspect","slug":"understand-me-if-you-refer-to-aspect","title":"Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network","date":"2021-08-05","arxiv_id":"2108.02352","n_code_links":1,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for-1","title":"WeChat Neural Machine Translation Systems for WMT21","date":"2021-08-05","arxiv_id":"2108.02401","n_code_links":0,"syntology":null},{"paper":"/paper/curriculum-learning-for-language-modeling","slug":"curriculum-learning-for-language-modeling","title":"Curriculum learning for language modeling","date":"2021-08-04","arxiv_id":"2108.02170","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spacemanidol/CurriculumLearningForLanguageModels"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"optimizing-latency-for-online-video","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","date":"2021-08-04","arxiv_id":"2108.02147","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-offset-block-embedding-array-robe-for","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","date":"2021-08-04","arxiv_id":"2108.02191","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dynamic-head-importance-computation","title":"A Dynamic Head Importance Computation Mechanism for Neural Machine Translation","date":"2021-08-03","arxiv_id":"2108.01377","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-multilingual-end-to-end-speech","slug":"a-study-of-multilingual-end-to-end-speech","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","date":"2021-08-03","arxiv_id":"2108.01280","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-feature-regularized-loss-for-weakly","title":"Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation","date":"2021-08-03","arxiv_id":"2108.01296","n_code_links":0,"syntology":null},{"paper":null,"slug":"exbert-an-external-knowledge-enhanced-bert","title":"ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference","date":"2021-08-03","arxiv_id":"2108.01589","n_code_links":0,"syntology":null},{"paper":null,"slug":"http2vec-embedding-of-http-requests-for","title":"HTTP2vec: Embedding of HTTP Requests for Detection of Anomalous Traffic","date":"2021-08-03","arxiv_id":"2108.01763","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-differentially-private-bert","title":"Large-Scale Differentially Private BERT","date":"2021-08-03","arxiv_id":"2108.01624","n_code_links":0,"syntology":null},{"paper":"/paper/q-pain-a-question-answering-dataset-to","slug":"q-pain-a-question-answering-dataset-to","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","date":"2021-08-03","arxiv_id":"2108.01764","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-with-progressive-sampling","slug":"vision-transformer-with-progressive-sampling","title":"Vision Transformer with Progressive Sampling","date":"2021-08-03","arxiv_id":"2108.01684","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yuexy/PS-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/changes-in-european-solidarity-before-and","slug":"changes-in-european-solidarity-before-and","title":"Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset","date":"2021-08-02","arxiv_id":"2108.01042","n_code_links":1,"syntology":null},{"paper":"/paper/congested-crowd-instance-localization-with","slug":"congested-crowd-instance-localization-with","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","date":"2021-08-02","arxiv_id":"2108.00584","n_code_links":1,"syntology":null},{"paper":"/paper/constrained-graphic-layout-generation-via","slug":"constrained-graphic-layout-generation-via","title":"Constrained Graphic Layout Generation via Latent Optimization","date":"2021-08-02","arxiv_id":"2108.00871","n_code_links":1,"syntology":null},{"paper":"/paper/lichee-improving-language-model-pre-training","slug":"lichee-improving-language-model-pre-training","title":"LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization","date":"2021-08-02","arxiv_id":"2108.00801","n_code_links":1,"syntology":null},{"paper":null,"slug":"musical-speech-a-transformer-based","title":"Musical Speech: A Transformer-based Composition Tool","date":"2021-08-02","arxiv_id":"2108.01043","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-aware-semi-autoregressive-semantic","title":"Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL","date":"2021-08-02","arxiv_id":"2108.00804","n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-neural-population","slug":"representation-learning-for-neural-population","title":"Representation learning for neural population activity with Neural Data Transformers","date":"2021-08-02","arxiv_id":"2108.01210","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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["snel-repo/neural-data-transformers"],"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":"self-supervised-answer-retrieval-on-clinical","title":"Self-supervised Answer Retrieval on Clinical Notes","date":"2021-08-02","arxiv_id":"2108.00775","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-for-mining-feature-requests","slug":"transfer-learning-for-mining-feature-requests","title":"Transfer Learning for Mining Feature Requests and Bug Reports from Tweets and App Store Reviews","date":"2021-08-02","arxiv_id":"2108.00663","n_code_links":1,"syntology":null},{"paper":null,"slug":"1213li-at-semeval-2021-task-6-detection-of","title":"1213Li at SemEval-2021 Task 6: Detection of Propaganda with Multi-modal Attention and Pre-trained Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bidirectional-transformer-based-alignment","title":"A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adept-an-adjective-dependent-plausibility","title":"ADEPT: An Adjective-Dependent Plausibility Task","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/are-pretrained-convolutions-better-than","slug":"are-pretrained-convolutions-better-than","title":"Are Pretrained Convolutions Better than Pretrained Transformers?","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"astartwice-at-semeval-2021-task-5-toxic-span","title":"AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attestable-at-semeval-2021-task-9-extending","slug":"attestable-at-semeval-2021-task-9-extending","title":"AttesTable at SemEval-2021 Task 9: Extending Statement Verification with Tables for Unknown Class, and Semantic Evidence Finding","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bennettnlp-at-semeval-2021-task-5-toxic-spans","title":"BennettNLP at SemEval-2021 Task 5: Toxic Spans Detection using Stacked Embedding Powered Toxic Entity Recognizer","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bertac-enhancing-transformer-based-language","slug":"bertac-enhancing-transformer-based-language","title":"BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-making-high-accuracy-non","title":"Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/beyond-sentence-level-end-to-end-speech","slug":"beyond-sentence-level-end-to-end-speech","title":"Beyond Sentence-Level End-to-End Speech Translation: Context Helps","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"can-transformer-models-measure-coherence-in","title":"Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cmta-covid-19-misinformation-multilingual","title":"CMTA: COVID-19 Misinformation Multilingual Analysis on Twitter","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-evidence-improves-monolingual","slug":"cross-lingual-evidence-improves-monolingual","title":"Cross-lingual Evidence Improves Monolingual Fake News Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-1-fusion-of","title":"CSECU-DSG at SemEval-2021 Task 1: Fusion of Transformer Models for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-5-leveraging","title":"CSECU-DSG at SemEval-2021 Task 5: Leveraging Ensemble of Sequence Tagging Models for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-6","title":"CSECU-DSG at SemEval-2021 Task 6: Orchestrating Multimodal Neural Architectures for Identifying Persuasion Techniques in Texts and Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"csecu-dsg-at-semeval-2021-task-7-detecting","title":"CSECU-DSG at SemEval-2021 Task 7: Detecting and Rating Humor and Offense Employing Transformers","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ctfn-hierarchical-learning-for-multimodal","slug":"ctfn-hierarchical-learning-for-multimodal","title":"CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-differential-amplifier-for-extractive","title":"Deep Differential Amplifier for Extractive Summarization","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deepblueai-at-semeval-2021-task-7-detecting","title":"DeepBlueAI at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Stacking Diverse Language Model-Based Methods","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dljust-at-semeval-2021-task-7-hahackathon","title":"DLJUST at SemEval-2021 Task 7: Hahackathon: Linking Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/early-detection-of-sexual-predators-in-chats","slug":"early-detection-of-sexual-predators-in-chats","title":"Early Detection of Sexual Predators in Chats","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ecco-an-open-source-library-for-the","slug":"ecco-an-open-source-library-for-the","title":"Ecco: An Open Source Library for the Explainability of Transformer Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emlm-a-new-pre-training-objective-for-emotion","slug":"emlm-a-new-pre-training-objective-for-emotion","title":"eMLM: A New Pre-training Objective for Emotion Related Tasks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/employing-argumentation-knowledge-graphs-for","slug":"employing-argumentation-knowledge-graphs-for","title":"Employing Argumentation Knowledge Graphs for Neural Argument Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"endtimes-at-semeval-2021-task-7-detecting-and","title":"EndTimes at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with BERT and Ensembles","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"es-just-at-semeval-2021-task-7-detecting-and","title":"ES-JUST at SemEval-2021 Task 7: Detecting and Rating Humor and Offensive Text Using Deep Learning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-contextualization-in-language","title":"Explaining Contextualization in Language Models using Visual Analytics","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explanations-for-commonsenseqa-new-dataset","slug":"explanations-for-commonsenseqa-new-dataset","title":"Explanations for CommonsenseQA: New Dataset and Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-listwise-evidence-reasoning-with-t5","title":"Exploring Listwise Evidence Reasoning with T5 for Fact Verification","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-neural-machine-translation","title":"Fast and Accurate Neural Machine Translation with Translation Memory","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ghost-at-semeval-2021-task-5-is-explanation","title":"GHOST at SemEval-2021 Task 5: Is explanation all you need?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ghostbert-generate-more-features-with-cheap","title":"GhostBERT: Generate More Features with Cheap Operations for BERT","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"grenzlinie-at-semeval-2021-task-7-detecting","title":"Grenzlinie at SemEval-2021 Task 7: Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gulu-at-semeval-2021-task-7-detecting-and","title":"Gulu at SemEval-2021 Task 7: Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/gx-at-semeval-2021-task-2-bert-with-lemma","slug":"gx-at-semeval-2021-task-2-bert-with-lemma","title":"GX at SemEval-2021 Task 2: BERT with Lemma Information for MCL-WiC Task","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hamiltondinggg-at-semeval-2021-task-5","title":"HamiltonDinggg at SemEval-2021 Task 5: Investigating Toxic Span Detection using RoBERTa Pre-training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-is-bert-without-word-ordering","title":"How effective is BERT without word ordering? Implications for language understanding and data privacy","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-many-layers-and-why-an-analysis-of-the","title":"How Many Layers and Why? An Analysis of the Model Depth in Transformers","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hub-at-semeval-2021-task-1-fusion-of-sentence","title":"hub at SemEval-2021 Task 1: Fusion of Sentence and Word Frequency to Predict Lexical Complexity","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hub-at-semeval-2021-task-2-word-meaning","title":"hub at SemEval-2021 Task 2: Word Meaning Similarity Prediction Model Based on RoBERTa and Word Frequency","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hub-at-semeval-2021-task-7-fusion-of-albert","title":"hub at SemEval-2021 Task 7: Fusion of ALBERT and Word Frequency Information Detecting and Rating Humor and Offense","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"iitk-lcp-at-semeval-2021-task-1-1","title":"IITK@LCP at SemEval-2021 Task 1: Classification for Lexical Complexity Regression Task","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/issues-with-entailment-based-zero-shot-text","slug":"issues-with-entailment-based-zero-shot-text","title":"Issues with Entailment-based Zero-shot Text Classification","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"jct-at-semeval-2021-task-1-context-aware","title":"JCT at SemEval-2021 Task 1: Context-aware Representation for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"just-blue-at-semeval-2021-task-1-predicting","title":"JUST-BLUE at SemEval-2021 Task 1: Predicting Lexical Complexity using BERT and RoBERTa Pre-trained Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kuileixi-a-chinese-open-ended-text-adventure","title":"KuiLeiXi: a Chinese Open-Ended Text Adventure Game","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/lasor-learning-accurate-3d-human-pose-and","slug":"lasor-learning-accurate-3d-human-pose-and","title":"LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering","date":"2021-08-01","arxiv_id":"2108.00351","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["iGame-Lab/LASOR"],"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":"lecun-at-semeval-2021-task-6-detecting","title":"LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"leebert-learned-early-exit-for-bert-with","title":"LeeBERT: Learned Early Exit for BERT with cross-level optimization","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"liori-at-semeval-2021-task-8-ask-transformer","title":"LIORI at SemEval-2021 Task 8: Ask Transformer for measurements","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lotus-at-semeval-2021-task-2-combination-of","title":"Lotus at SemEval-2021 Task 2: Combination of BERT and Paraphrasing for English Word Sense Disambiguation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"measure-and-evaluation-of-semantic-divergence","title":"Measure and Evaluation of Semantic Divergence across Two Languages","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-and-improving-bert-s-mathematical-1","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning.","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"medai-at-semeval-2021-task-5-start-to-end","title":"MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mind-at-semeval-2021-task-6-propaganda","title":"MinD at SemEval-2021 Task 6: Propaganda Detection using Transfer Learning and Multimodal Fusion","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-task-aware-mimo-cardinality-for","title":"Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/more-than-text-multi-modal-chinese-word","slug":"more-than-text-multi-modal-chinese-word","title":"More than Text: Multi-modal Chinese Word Segmentation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-head-highly-parallelized-lstm-decoder","title":"Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mvp-bert-multi-vocab-pre-training-for-chinese","title":"MVP-BERT: Multi-Vocab Pre-training for Chinese BERT","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-metaphor-detection-with-visibility","title":"Neural Metaphor Detection with Visibility Embeddings","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nlpiitr-at-semeval-2021-task-6-roberta-model","title":"NLPIITR at SemEval-2021 Task 6: RoBERTa Model with Data Augmentation for Persuasion Techniques Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nlyticsfkie-at-semeval-2021-task-6-detection","title":"NLyticsFKIE at SemEval-2021 Task 6: Detection of Persuasion Techniques In Texts And Images","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre-1","title":"nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-differences-between-bert-and-mt","title":"On the differences between BERT and MT encoder spaces and how to address them in translation tasks","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"paw-at-semeval-2021-task-2-multilingual-and","title":"PAW at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation : Exploring Cross Lingual Transfer, Augmentations and Adversarial Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pingan-omini-sinitic-at-semeval-2021-task-4","title":"PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/plome-pre-training-with-misspelled-knowledge","slug":"plome-pre-training-with-misspelled-knowledge","title":"PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"point-disambiguate-and-copy-incorporating","title":"Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pral-a-tailored-pre-training-model-for-task","title":"PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-pragmatic-discourse-features-in","title":"Predicting pragmatic discourse features in the language of adults with autism spectrum disorder","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"raw-c-relatedness-of-ambiguous-words-in-1","title":"RAW-C: Relatedness of Ambiguous Words in Context (A New Lexical Resource for English)","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"rg-pa-at-semeval-2021-task-1-a-contextual","title":"RG PA at SemEval-2021 Task 1: A Contextual Attention-based Model with RoBERTa for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sarcasmdet-at-semeval-2021-task-7-detect","title":"SarcasmDet at SemEval-2021 Task 7: Detect Humor and Offensive based on Demographic Factors using RoBERTa Pre-trained Model","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sefamerve-arge-at-semeval-2021-task-5-toxic","slug":"sefamerve-arge-at-semeval-2021-task-5-toxic","title":"Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"skoltechnlp-at-semeval-2021-task-5-leveraging","title":"SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stanford-mlab-at-semeval-2021-task-8-48-hours","title":"Stanford MLab at SemEval-2021 Task 8: 48 Hours Is All You Need","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stretch-vst-getting-flexible-with-visual","title":"Stretch-VST: Getting Flexible With Visual Stories","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"d9e2890f10b1cc22eaf45826f96c9bed7a9fdf5b851d1e34d6d36e1080a42b52","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}