Abstract
This paper describes a memory-based machine translation system developed for the Semantic Net- work Array Processor (SNAP). The goal of our work is to develop a scalable and high-performance memory-based machine translation system which utilizes the high degree of parallelism provided by the SNAP machine. We have implemented an experimental machine translation system DMSNAP as a central part of a real-time speech-to-speech dia- logue translation system. It is a SNAP version of the ΦDMDIALOG speech-to-speech translation system. Memory-based natural language processing and syntactic constraint network model has been incorporated using parallel marker-passing which is directly supported from hardware level. Experimental results demonstrate that the parsing of a sentence is done in the order of milliseconds.- Anthology ID:
- 1991.mtsummit-papers.15
- Volume:
- Proceedings of Machine Translation Summit III: Papers
- Month:
- July 1-4
- Year:
- 1991
- Address:
- Washington DC, USA
- Venue:
- MTSummit
- SIG:
- Publisher:
- Note:
- Pages:
- 93–100
- Language:
- URL:
- https://aclanthology.org/1991.mtsummit-papers.15
- DOI:
- Cite (ACL):
- Hiroaki Kitano, Dan Moldovan, and Seungho Cha. 1991. Toward High Performance Machine Translation: Preliminary Results from Massively Parallel Memory-Based Translation on SNAP. In Proceedings of Machine Translation Summit III: Papers, pages 93–100, Washington DC, USA.
- Cite (Informal):
- Toward High Performance Machine Translation: Preliminary Results from Massively Parallel Memory-Based Translation on SNAP (Kitano et al., MTSummit 1991)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/1991.mtsummit-papers.15.pdf