Mask-combine Decoding and Classification Approach for Punctuation Prediction with real-time Inference Constraints
원문 초록
In this work, we unify several existing decoding strategies for punctuation prediction in one framework and introduce a novel strategy which utilises multiple predictions at each word across different windows. We show that significant improvements can be achieved by optimising these strategies after training a model, only leading to a potential increase in inference time, with no requirement for retraining. We further use our decoding strategy framework for the first comparison of tagging and classification approaches for punctuation prediction in a real-time setting. Our results show that a classification approach for punctuation prediction can be beneficial when little or no right-side context is available.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Open-World Social Event Classification
Semi-supervised Time Series Classification by Temporal Relation Prediction
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
Hybrid-View Attention for csPCa Classification in TRUS
토론
이 논문과 연결된 포럼 글이 아직 없습니다.