Abstract
Using a corpus of compiled codes from U.S. states containing labeled tax law sections, we train text classifiers to automatically tag tax-law documents and, further, to identify the associated revenue source (e.g. income, property, or sales). After evaluating classifier performance in held-out test data, we apply them to an historical corpus of U.S. state legislation to extract the flow of relevant laws over the years 1910 through 2010. We document that the classifiers are effective in the historical corpus, for example by automatically detecting establishments of state personal income taxes. The trained models with replication code are published at https://github.com/luyang521/tax-classification.- Anthology ID:
- 2021.nllp-1.7
- Volume:
- Proceedings of the Natural Legal Language Processing Workshop 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Nikolaos Aletras, Ion Androutsopoulos, Leslie Barrett, Catalina Goanta, Daniel Preotiuc-Pietro
- Venue:
- NLLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 76–85
- Language:
- URL:
- https://aclanthology.org/2021.nllp-1.7
- DOI:
- 10.18653/v1/2021.nllp-1.7
- Cite (ACL):
- Elliott Ash, Malka Guillot, and Luyang Han. 2021. Machine Extraction of Tax Laws from Legislative Texts. In Proceedings of the Natural Legal Language Processing Workshop 2021, pages 76–85, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Machine Extraction of Tax Laws from Legislative Texts (Ash et al., NLLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.nllp-1.7.pdf
- Code
- luyang521/tax-classification