Showing 1–20 of 44 results
/ Date/ Name
Feb 6, 2021Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic LabelingJun 27, 2025AutoMixer: Checkpoint Artifacts as Automatic Data MixersMar 16, 2017Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity ModelAug 14, 2021The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text GenerationFeb 6, 2021Neural Data-to-Text Generation with LM-based Text AugmentationFeb 6, 2021Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum LearningOct 21, 2020Safe Handover in Mixed-Initiative Control for Cyber-Physical SystemsMar 18, 2020Unsupervised Pidgin Text Generation By Pivoting English Data and Self-TrainingOct 8, 2020DART: A Lightweight Quality-Suggestive Data-to-Text Annotation ToolJul 7, 2021Time-Aware Ancient Chinese Text Translation and InferenceJul 7, 2021On Training Instance Selection for Few-Shot Neural Text GenerationMay 3, 2020Neural Data-to-Text Generation via Jointly Learning the Segmentation and CorrespondenceSep 14, 2023Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech RecognitionNov 1, 2023On The Open Prompt Challenge In Conditional Audio GenerationMay 4, 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News TranslationMar 18, 2025Self-Vocabularizing Training for Neural Machine TranslationApr 7, 2026Short Data, Long Context: Distilling Positional Knowledge in TransformersApr 14, 2026RPRA: Predicting an LLM-Judge for Efficient but Performant InferenceJul 4, 2025IMPACT: Importance-Aware Activation Space ReconstructionAug 27, 2022MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages