Abstract
In this paper, the major problems of the current machine translation systems are first outlined. A new direction, highlighting the system capability to be customizable and self-learnable, is then proposed for attacking the described problems, which are mainly resulted from the very complicated characteristics of natural languages. The proposed solution adopts an unsupervised two-way training mechanism and a parameterized architecture to acquire the required statistical knowledge, such that the system can be easily adapted to different domains and various preferences of individual users.- Anthology ID:
- 1999.mtsummit-1.29
- Volume:
- Proceedings of Machine Translation Summit VII
- Month:
- September 13-17
- Year:
- 1999
- Address:
- Singapore, Singapore
- Venue:
- MTSummit
- SIG:
- Publisher:
- Note:
- Pages:
- 182–190
- Language:
- URL:
- https://aclanthology.org/1999.mtsummit-1.29
- DOI:
- Cite (ACL):
- Keh-Yih Su and Jing-Shin Chang. 1999. A customizable, self-learning parameterized MT system: the next generation. In Proceedings of Machine Translation Summit VII, pages 182–190, Singapore, Singapore.
- Cite (Informal):
- A customizable, self-learning parameterized MT system: the next generation (Su & Chang, MTSummit 1999)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/1999.mtsummit-1.29.pdf