Abstract
This paper proposes to enrich RBMT dictionaries with Named Entities (NEs) automatically acquired from Wikipedia. The method is applied to the Apertium English–Spanish system and its performance compared to that of Apertium with and without handtagged NEs. The system with automatic NEs outperforms the one without NEs, while results vary when compared to a system with handtagged NEs (results are comparable for Spanish→English but slightly worst for English→Spanish). Apart from that, adding automatic NEs contributes to decreasing the amount of unknown terms by more than 10%.- Anthology ID:
- 2011.freeopmt-1.7
- Volume:
- Proceedings of the Second International Workshop on Free/Open-Source Rule-Based Machine Translation
- Month:
- January 20-21
- Year:
- 2011
- Address:
- Barcelona, Spain
- Editors:
- Felipe Sánchez-Martinez, Juan Antonio Pérez-Ortiz
- Venue:
- FreeOpMT
- SIG:
- Publisher:
- Note:
- Pages:
- 37–44
- Language:
- URL:
- https://aclanthology.org/2011.freeopmt-1.7
- DOI:
- Cite (ACL):
- Antonio Toral and Andy Way. 2011. Automatic acquisition of named entities for rule-based machine translation. In Proceedings of the Second International Workshop on Free/Open-Source Rule-Based Machine Translation, pages 37–44, Barcelona, Spain.
- Cite (Informal):
- Automatic acquisition of named entities for rule-based machine translation (Toral & Way, FreeOpMT 2011)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/2011.freeopmt-1.7.pdf