In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representation model, which includes BERT, ELMo, and GPT. These developments have led to the conviction that previous-generation, shallower neural networks for language understanding are obsolete. In this paper, however, we demonstrate that rudimentary, lightweight neural networks can still be made competitive without architecture changes, external training data, or additional input features. We propose to distill knowledge from BERT, a state-of-the-art language representation model, into a single-layer BiLSTM, as well as its siamese counterpart for sentence-pair tasks. Across multiple datasets in paraphrasing, natural language inference, and sentiment classification, we achieve comparable results with ELMo, while using roughly 100 times fewer parameters and 15 times less inference time.
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
Raphael Tang,Yao Lu,Linqing Liu,Lili Mou,Olga Vechtomova,Jimmy J. Lin
Published 2019 in arXiv.org
ABSTRACT
PUBLICATION RECORD
- Publication year
2019
- Venue
arXiv.org
- Publication date
2019-03-28
- Fields of study
Linguistics, Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-39 of 39 references · Page 1 of 1