Search Results for author:
Found 4 papers, 2 papers with code
Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage.
Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
The increasing size of language models raises great research interests in parameter-efficient fine-tuning such as LoRA that freezes the pre-trained model, and injects small-scale trainable parameters for multiple downstream tasks (e. g., summarization, question answering and translation).
Leveraging Summary Guidance on Medical Report Summarization
This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derived from MIMIC-III, respectively.
Differentiable N-gram Objective on Abstractive Summarization
ROUGE is a standard automatic evaluation metric based on n-grams for sequence-to-sequence tasks, while cross-entropy loss is an essential objective of neural network language model that optimizes at a unigram level.
