Reconsidering Token Embeddings with the Definitions for Pre-trained Language Models
Zhang, Ying, Li, Dongyuan, Okumura, Manabu
–arXiv.org Artificial Intelligence
Learning token embeddings based on token co-occurrence statistics has proven effective for both pre-training and fine-tuning in natural language processing. However, recent studies have pointed out the distribution of learned embeddings degenerates into anisotropy, and even pre-trained language models (PLMs) suffer from a loss of semantics-related information in embeddings for low-frequency tokens. This study first analyzes fine-tuning dynamics of a PLM, BART-large, and demonstrates its robustness against degeneration. On the basis of this finding, we propose DefinitionEMB, a method that utilizes definitions to construct isotropically distributed and semantics-related token embeddings for PLMs while maintaining original robustness during fine-tuning. Our experiments demonstrate the effectiveness of leveraging definitions from Wiktionary to construct such embeddings for RoBERTa-base and BART-large. Furthermore, the constructed embeddings for low-frequency tokens improve the performance of these models across various GLUE and four text summarization datasets.
arXiv.org Artificial Intelligence
Aug-2-2024
- Country:
- North America > United States
- California (0.04)
- Europe
- Asia > Japan
- Honshū > Kantō > Tokyo Metropolis Prefecture > Tokyo (0.04)
- North America > United States
- Genre:
- Research Report
- New Finding (0.46)
- Experimental Study (0.46)
- Research Report
- Industry:
- Leisure & Entertainment (0.93)
- Law (0.93)
- Media > Film (0.67)
- Government (0.67)
- Technology: