Abstract
In this paper, we trace the history of neural networks applied to natural language understanding tasks, and identify key contributions which the nature of language has made to the development of neural network architectures. We focus on the importance of variable binding and its instantiation in attention-based models, and argue that Transformer is not a sequence model but an induced-structure model. This perspective leads to predictions of the challenges facing research in deep learning architectures for natural language understanding.- Anthology ID:
- 2020.acl-main.561
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6294–6306
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.561
- DOI:
- 10.18653/v1/2020.acl-main.561
- Cite (ACL):
- James Henderson. 2020. The Unstoppable Rise of Computational Linguistics in Deep Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6294–6306, Online. Association for Computational Linguistics.
- Cite (Informal):
- The Unstoppable Rise of Computational Linguistics in Deep Learning (Henderson, ACL 2020)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/2020.acl-main.561.pdf