4 papers
The Maskability Index: Predicting Task-Objective Alignment in Pretrained Language Models
Ahmad Pouramini, Mahsa Afsharzadeh
Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating structured knowledge. However, their performance depends on how clos…
Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning
Ahmad Pouramini, Mahsa Afsharizadeh
This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural lang…
Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models
Ahmad Pouramini, Hesham Faili
Prompt-based learning has emerged as a dominant paradigm in natural language processing. This study explores the impact of diverse pre-training objectives on the performance of enc…
CrossPT: Exploring Cross-Task Transferability through Multi-Task Prompt Tuning
Ahmad Pouramini, Hesham Faili
Prompt tuning offers a parameter-efficient way to adapt large pre-trained language models to new tasks, but most existing approaches are designed for single-task settings, failing…