{"total":242,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329,"area":null},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225,"area":null},{"id":"2206.08317","title":"Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition","created":"2022-06-16","cited_by_count":144,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2105.14686","title":"Fully Hyperbolic Neural Networks","created":"2021-05-31","cited_by_count":108,"area":null},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2110.09681","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","created":"2021-10-19","cited_by_count":68,"area":null},{"id":"2108.01210","title":"Representation learning for neural population activity with Neural Data Transformers","created":"2021-08-02","cited_by_count":50,"area":null},{"id":"2203.14966","title":"Error Correction Code Transformer","created":"2022-03-27","cited_by_count":47,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2102.02810","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","created":"2021-02-04","cited_by_count":41,"area":null},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41,"area":null},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40,"area":null},{"id":"2109.00799","title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","created":"2021-09-02","cited_by_count":39,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"area":null},{"id":"2104.08308","title":"Neural Transfer Learning for Repairing Security Vulnerabilities in C Code","created":"2021-04-16","cited_by_count":36,"area":null},{"id":"2104.08400","title":"Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs","created":"2021-04-16","cited_by_count":36,"area":null},{"id":"2102.02723","title":"Data-to-text Generation with Macro Planning","created":"2021-02-04","cited_by_count":34,"area":null},{"id":"2105.11098","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","created":"2021-05-24","cited_by_count":34,"area":null},{"id":"2212.04972","title":"MOPRD: A multidisciplinary open peer review dataset","created":"2022-12-09","cited_by_count":32,"area":null},{"id":"2104.00290","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","created":"2021-04-01","cited_by_count":31,"area":null},{"id":"2407.17492","title":"Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry","created":"2024-07-04","cited_by_count":31,"area":null},{"id":"2109.01135","title":"Sequence-to-Sequence Learning with Latent Neural Grammars","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2105.06947","title":"Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer","created":"2021-05-14","cited_by_count":28,"area":null},{"id":"2105.07476","title":"Data Augmentation for Sign Language Gloss Translation","created":"2021-05-16","cited_by_count":28,"area":null},{"id":"2305.15678","title":"Revisiting non-English Text Simplification: A Unified Multilingual Benchmark","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2407.18698","title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","created":"2024-07-26","cited_by_count":27,"area":null},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26,"area":null},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2109.06133","title":"Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization","created":"2021-09-13","cited_by_count":22,"area":null},{"id":"2103.08862","title":"Gumbel-Attention for Multi-modal Machine Translation","created":"2021-03-16","cited_by_count":20,"area":null},{"id":"2106.06797","title":"Machine Translation into Low-resource Language Varieties","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2212.06385","title":"TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2104.07896","title":"Generating Bug-Fixes Using Pretrained Transformers","created":"2021-04-16","cited_by_count":18,"area":null},{"id":"2104.14272","title":"Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks","created":"2021-04-29","cited_by_count":18,"area":null},{"id":"2106.16036","title":"A Generative Model for Raw Audio Using Transformer Architectures","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2105.13072","title":"TranSmart: A Practical Interactive Machine Translation System","created":"2021-05-27","cited_by_count":17,"area":null},{"id":"2202.13756","title":"Data-to-text Generation with Variational Sequential Planning","created":"2022-02-28","cited_by_count":17,"area":null},{"id":"2206.11925","title":"Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets","created":"2022-06-23","cited_by_count":17,"area":null},{"id":"2104.04345","title":"A Graph VAE and Graph Transformer Approach to Generating Molecular Graphs","created":"2021-04-09","cited_by_count":16,"area":null},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2206.00330","title":"B2T Connection: Serving Stability and Performance in Deep Transformers","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2503.04598","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2101.02046","title":"TextBox: A Unified, Modularized, and Extensible Framework for Text Generation","created":"2021-01-06","cited_by_count":15,"area":null},{"id":"2310.14777","title":"Geographical Erasure in Language Generation","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2101.09765","title":"Belief-based Generation of Argumentative Claims","created":"2021-01-24","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":"2106.04718","title":"FastSeq: Make Sequence Generation Faster","created":"2021-06-08","cited_by_count":13,"area":null},{"id":"2111.10746","title":"Capitalization and Punctuation Restoration: a Survey","created":"2021-11-21","cited_by_count":13,"area":null},{"id":"2205.01133","title":"Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation","created":"2022-05-02","cited_by_count":13,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12,"area":null},{"id":"2411.11295","title":"Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2105.12172","title":"IntelliCAT: Intelligent Machine Translation Post-Editing with Quality Estimation and Translation Suggestion","created":"2021-05-25","cited_by_count":11,"area":null},{"id":"2301.00969","title":"Boosting Neural Networks to Decompile Optimized Binaries","created":"2023-01-03","cited_by_count":11,"area":null},{"id":"2106.06200","title":"Towards User-Driven Neural Machine Translation","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2201.02550","title":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","created":"2022-01-07","cited_by_count":10,"area":null},{"id":"2202.09509","title":"PETCI: A Parallel English Translation Dataset of Chinese Idioms","created":"2022-02-19","cited_by_count":10,"area":null},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2210.10914","title":"Prophet Attention: Predicting Attention with Future Attention for Image Captioning","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2102.09395","title":"Robust PDF Document Conversion Using Recurrent Neural Networks","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2111.10770","title":"Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism","created":"2021-11-21","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":"2301.08115","title":"Language Embeddings Sometimes Contain Typological Generalizations","created":"2023-01-19","cited_by_count":9,"area":null},{"id":"2304.14395","title":"string2string: A Modern Python Library for String-to-String Algorithms","created":"2023-04-27","cited_by_count":9,"area":null},{"id":"2403.01196","title":"Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021","created":"2024-03-02","cited_by_count":9,"area":null},{"id":"2403.01985","title":"Transformers for Low-Resource Languages: Is F\\'eidir Linn!","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2405.04050","title":"Learning Linear Block Error Correction Codes","created":"2024-05-07","cited_by_count":9,"area":null},{"id":"2102.10160","title":"Multi-Domain Adaptation in Neural Machine Translation Through Multidimensional Tagging","created":"2021-02-19","cited_by_count":8,"area":null},{"id":"2104.14671","title":"SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics","created":"2021-04-29","cited_by_count":8,"area":null},{"id":"2105.05542","title":"!Qu\\'e maravilla! Multimodal Sarcasm Detection in Spanish: a Dataset and a Baseline","created":"2021-05-12","cited_by_count":8,"area":null},{"id":"2105.11872","title":"Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling","created":"2021-05-25","cited_by_count":8,"area":null},{"id":"2106.02082","title":"Language Embeddings for Typology and Cross-lingual Transfer Learning","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2110.13721","title":"Geometric Transformer for End-to-End Molecule Properties Prediction","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2111.03800","title":"Finnish Dialect Identification: The Effect of Audio and Text","created":"2021-11-06","cited_by_count":8,"area":null},{"id":"2201.01880","title":"Automatic Related Work Generation: A Meta Study","created":"2022-01-06","cited_by_count":8,"area":null},{"id":"2201.12475","title":"Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer","created":"2022-01-29","cited_by_count":8,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2211.15578","title":"Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality","created":"2022-11-28","cited_by_count":8,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2103.04353","title":"Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data","created":"2021-03-07","cited_by_count":7,"area":null},{"id":"2108.11126","title":"YANMTT: Yet Another Neural Machine Translation Toolkit","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2109.01935","title":"Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case","created":"2021-09-04","cited_by_count":7,"area":null},{"id":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2208.00176","title":"ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls","created":"2022-07-30","cited_by_count":7,"area":null},{"id":"2210.17246","title":"Tables to LaTeX: structure and content extraction from scientific tables","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2301.08008","title":"Improving Machine Translation with Phrase Pair Injection and Corpus Filtering","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2407.21139","title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2412.05269","title":"Chemist-aligned retrosynthesis by ensembling diverse inductive bias models","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2101.01447","title":"End-to-End Video Question-Answer Generation with Generator-Pretester Network","created":"2021-01-05","cited_by_count":6,"area":null},{"id":"2103.16789","title":"An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2106.01400","title":"Dual Script E2E framework for Multilingual and Code-Switching ASR","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2111.04574","title":"Detecting Depression in Thai Blog Posts: a Dataset and a Baseline","created":"2021-11-08","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":"2210.12273","title":"Graphemic Normalization of the Perso-Arabic Script","created":"2022-10-21","cited_by_count":6,"area":null}],"next_cursor":"100"}