Abstract
We introduce structured projection of intermediate gradients (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e.g., parsing) in intermediate layers. SPIGOT requires no marginal inference, unlike structured attention networks and reinforcement learning-inspired solutions. Like so-called straight-through estimators, SPIGOT defines gradient-like quantities associated with intermediate nondifferentiable operations, allowing backpropagation before and after them; SPIGOT’s proxy aims to ensure that, after a parameter update, the intermediate structure will remain well-formed. We experiment on two structured NLP pipelines: syntactic-then-semantic dependency parsing, and semantic parsing followed by sentiment classification. We show that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing.- Anthology ID:
- P18-1173
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1863–1873
- Language:
- URL:
- https://aclanthology.org/P18-1173
- DOI:
- 10.18653/v1/P18-1173
- Cite (ACL):
- Hao Peng, Sam Thomson, and Noah A. Smith. 2018. Backpropagating through Structured Argmax using a SPIGOT. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1863–1873, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Backpropagating through Structured Argmax using a SPIGOT (Peng et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P18-1173.pdf
- Code
- Noahs-ARK/SPIGOT