{"total":151,"rows":[{"id":"2210.10341","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","created":"2022-10-19","cited_by_count":538,"area":null},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406,"area":null},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88,"area":null},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2109.09193","title":"Towards Zero-Label Language Learning","created":"2021-09-19","cited_by_count":76,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2103.07665","title":"Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction","created":"2021-03-13","cited_by_count":40,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"area":null},{"id":"2203.10940","title":"Quality Controlled Paraphrase Generation","created":"2022-03-21","cited_by_count":31,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2109.10678","title":"Natural Language Video Localization with Learnable Moment Proposals","created":"2021-09-22","cited_by_count":27,"area":null},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27,"area":null},{"id":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2205.04980","title":"ALLSH: Active Learning Guided by Local Sensitivity and Hardness","created":"2022-05-10","cited_by_count":23,"area":null},{"id":"2308.06009","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","created":"2023-08-11","cited_by_count":22,"area":null},{"id":"2204.05515","title":"CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection","created":"2022-04-12","cited_by_count":21,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2310.18365","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2110.07582","title":"Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding","created":"2021-10-14","cited_by_count":19,"area":null},{"id":"2105.02274","title":"Rethinking Search: Making Domain Experts out of Dilettantes","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2104.07064","title":"Is Everything in Order? A Simple Way to Order Sentences","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2210.15221","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2103.07011","title":"Towards Socially Intelligent Agents with Mental State Transition and Human Utility","created":"2021-03-12","cited_by_count":14,"area":null},{"id":"2103.12876","title":"Complex Factoid Question Answering with a Free-Text Knowledge Graph","created":"2021-03-23","cited_by_count":14,"area":null},{"id":"2109.10604","title":"NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset","created":"2021-09-22","cited_by_count":14,"area":null},{"id":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2105.07654","title":"Dependency Parsing as MRC-based Span-Span Prediction","created":"2021-05-17","cited_by_count":13,"area":null},{"id":"2101.06883","title":"CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering","created":"2021-01-18","cited_by_count":12,"area":null},{"id":"2211.10330","title":"GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation","created":"2022-11-18","cited_by_count":11,"area":null},{"id":"2212.13023","title":"Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal","created":"2022-12-26","cited_by_count":11,"area":null},{"id":"2305.16585","title":"ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2108.11703","title":"Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation","created":"2021-08-26","cited_by_count":10,"area":null},{"id":"2112.04735","title":"From Good to Best: Two-Stage Training for Cross-lingual Machine Reading Comprehension","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2112.11916","title":"ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification","created":"2021-12-16","cited_by_count":10,"area":null},{"id":"2305.16663","title":"GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2105.09043","title":"Sentence Extraction-Based Machine Reading Comprehension for Vietnamese","created":"2021-05-19","cited_by_count":9,"area":null},{"id":"2207.06872","title":"Data Augmentation for Low-Resource Quechua ASR Improvement","created":"2022-07-14","cited_by_count":9,"area":null},{"id":"2404.00415","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","created":"2024-03-30","cited_by_count":9,"area":null},{"id":"2101.05469","title":"Text Augmentation in a Multi-Task View","created":"2021-01-14","cited_by_count":8,"area":null},{"id":"2101.11178","title":"Neural Sentence Ordering Based on Constraint Graphs","created":"2021-01-27","cited_by_count":8,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2406.04286","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2203.16794","title":"MMER: Multimodal Multi-task Learning for Speech Emotion Recognition","created":"2022-03-31","cited_by_count":7,"area":null},{"id":"2204.11205","title":"EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification","created":"2022-04-24","cited_by_count":7,"area":null},{"id":"2206.07117","title":"TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation","created":"2022-06-14","cited_by_count":7,"area":null},{"id":"2210.14823","title":"Visual Answer Localization with Cross-modal Mutual Knowledge Transfer","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2102.01226","title":"Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data","created":"2021-02-01","cited_by_count":6,"area":null},{"id":"2103.00293","title":"N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking","created":"2021-02-27","cited_by_count":6,"area":null},{"id":"2104.00234","title":"A Survey on Natural Language Video Localization","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2110.03269","title":"Multi-tasking Dialogue Comprehension with Discourse Parsing","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2204.00291","title":"Text-To-Speech Data Augmentation for Low Resource Speech Recognition","created":"2022-04-01","cited_by_count":6,"area":null},{"id":"2210.10343","title":"Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2212.13163","title":"MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding","created":"2022-12-26","cited_by_count":6,"area":null},{"id":"2405.00980","title":"A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2201.02489","title":"Semantic-based Data Augmentation for Math Word Problems","created":"2022-01-07","cited_by_count":5,"area":null},{"id":"2204.12293","title":"Contrastive Language-Action Pre-training for Temporal Localization","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2209.01560","title":"Selective Text Augmentation with Word Roles for Low-Resource Text Classification","created":"2022-09-04","cited_by_count":5,"area":null},{"id":"2304.07611","title":"A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2305.13623","title":"Validating Multimedia Content Moderation Software via Semantic Fusion","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2310.05296","title":"Tailoring Self-Attention for Graph via Rooted Subtrees","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2402.13576","title":"Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2504.01476","title":"Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2101.06400","title":"ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks","created":"2021-01-16","cited_by_count":4,"area":null},{"id":"2112.06109","title":"Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models","created":"2021-12-12","cited_by_count":4,"area":null},{"id":"2203.15285","title":"Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching","created":"2022-03-29","cited_by_count":4,"area":null},{"id":"2305.08502","title":"MeeQA: Natural Questions in Meeting Transcripts","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2310.09619","title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2402.13566","title":"Event-aware Video Corpus Moment Retrieval","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2501.18649","title":"Fake News Detection After LLM Laundering: Measurement and Explanation","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2103.05841","title":"Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance","created":"2021-03-10","cited_by_count":3,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2107.10474","title":"Back-Translated Task Adaptive Pretraining: Improving Accuracy and Robustness on Text Classification","created":"2021-07-22","cited_by_count":3,"area":null},{"id":"2109.08754","title":"Semi-Supervised Few-Shot Intent Classification and Slot Filling","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2203.00354","title":"Improving Performance of Automated Essay Scoring by using back-translation essays and adjusted scores","created":"2022-03-01","cited_by_count":3,"area":null},{"id":"2203.02753","title":"Feeding What You Need by Understanding What You Learned","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2206.02734","title":"Global Mixup: Eliminating Ambiguity with Clustering","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2209.08898","title":"Batch Layer Normalization, A new normalization layer for CNNs and RNN","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2307.09021","title":"Towards a Neural Era in Dialogue Management for Collaboration: A Literature Survey","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2309.04739","title":"Data Augmentation for Conversational AI","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2401.11373","title":"Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion","created":"2024-01-21","cited_by_count":3,"area":null},{"id":"2104.08268","title":"Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2107.00368","title":"Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems","created":"2021-07-01","cited_by_count":2,"area":null}],"next_cursor":"100"}