Abstract
The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at https://github.com/harvardnlp/pytorch-struct.- Anthology ID:
- 2020.acl-demos.38
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Asli Celikyilmaz, Tsung-Hsien Wen
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 335–342
- Language:
- URL:
- https://aclanthology.org/2020.acl-demos.38
- DOI:
- 10.18653/v1/2020.acl-demos.38
- Award:
- Honorable Mention for Best Demonstration Paper
- Cite (ACL):
- Alexander Rush. 2020. Torch-Struct: Deep Structured Prediction Library. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 335–342, Online. Association for Computational Linguistics.
- Cite (Informal):
- Torch-Struct: Deep Structured Prediction Library (Rush, ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.acl-demos.38.pdf
- Code
- harvardnlp/pytorch-struct