Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework
Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization
with the help of salient information identified by the extractive model. Previous works that …
with the help of salient information identified by the extractive model. Previous works that …
Improving Copy-oriented Text Generation via EDU Copy Mechanism
T Wu, H Chen, L Qin, Z Cao, C Ai - Proceedings of the 2024 Joint …, 2024 - aclanthology.org
Many text generation tasks are copy-oriented. For instance, nearly 30% content of news
summaries is copied. The copy rate is even higher in Grammatical Error Correction (GEC) …
summaries is copied. The copy rate is even higher in Grammatical Error Correction (GEC) …
On Cross-Domain Pre-Trained Language Models for Clinical Text Mining: How Do They Perform on Data-Constrained Fine-Tuning?
S Belkadi, L Han, Y Wu, V Antonini… - arXiv preprint arXiv …, 2022 - arxiv.org
Fine-tuning Large Language Models (LLMs) pre-trained from general or related domain
data to a specific domain and task using a limited amount of resources available in the new …
data to a specific domain and task using a limited amount of resources available in the new …
Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition
The practice of fine-tuning Pre-trained Language Models (PLMs) from general or domain-
specific data to a specific task with limited resources, has gained popularity within the field of …
specific data to a specific task with limited resources, has gained popularity within the field of …