4 papers
Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky
An ideal length-extrapolatable Transformer language model can handle sequences longer than the training length without any fine-tuning. Such long-context utilization capability rel…
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang +1
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural…
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen +2
The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further e…
Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation
Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky +1
Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transform…