Abstract
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.- Anthology ID:
- P17-1105
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1139–1149
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/P17-1105/
- DOI:
- 10.18653/v1/P17-1105
- Cite (ACL):
- Maxim Rabinovich, Mitchell Stern, and Dan Klein. 2017. Abstract Syntax Networks for Code Generation and Semantic Parsing. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1139–1149, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Abstract Syntax Networks for Code Generation and Semantic Parsing (Rabinovich et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/P17-1105.pdf
- Data
- ATIS