| |
|
Machine translation (MT) is more important than ever. The quality of MT output has increased substantially in recent years, due to more sophisticated utilization of statistical learning methods and objective evaluation methods. However, statistical MT (SMT) systems often generate "word salad," where the output may contain many correct words but in the wrong order, making it hard to understand. We propose to investigate a new approach to SMT that has models of word order at its core, in contrast to other syntax-based approaches. Models that integrate word order more directly promise to greatly improve the readability of translations. Our research will simultaneously focus on two language pairs -- English/French and English/Arabic -- thus demonstrating the generality of the approach. In addition to improved MT, goals of the workshop include training students to contribute to MT and NLP research for years to come, and a complete easy-to-use reference implementation for worldwide distribution. | |||
| |||
|
| |||
| Team Members: | |||
| Dan Melamed | Team Leader | New York University | |
| Stephen Clark | Team Co-Leader | Oxford University | |
| Andy Way | Team Co-Leader | Dublin City University | |
| Dekai Wu | Team Co-Leader | Hong Kong University of Science and Technology | |
| Keith Hall | Senior Researcher | Johns Hopkins University | |
| Mary Hearne | Senior Researcher | Dublin City University | |
| Marine Carpuat | Graduate Student | Hong Kong University of Science and Technology | |
| Markus Dreyer | Graduate Student | Johns Hopkins University | |
| Declan Groves | Graduate Student | Dublin City University | |
| Yihai Shen | Graduate Student | Hong Kong University of Science and Technology | |
| Ben Wellington | Graduate Student | New York University | |
| Andrea Burbank | Undergraduate Student | Stanford University | |
| Pamela Fox | Undergraduate Student | University of Southern California | |
| Technical Contact: Dan Melamed Computer Science Department New York University |
Administrative Contact: 2005 Summer Workshop Center for Language and Speech Processing Johns Hopkins University |
||