| 题名: | improving phrase-based smt model with flattened bilingual parse tree |
| 作者: | Zhang Dakun
; Sun Le
; Li Wenbo
|
| 会议文集: | Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010
|
| 会议名称: | 6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010
|
| 会议日期: | August 21,
|
| 出版日期: | 2010
|
| 会议地点: | Beijing, China
|
| 关键词: | Computational linguistics
; Feature extraction
; Information theory
; Knowledge engineering
; Natural language processing systems
; Speech transmission
; Syntactics
|
| 出版地: | United States
|
| ISBN: | 9781420000000
|
| 部门归属: | (1) Institute of Software, Chinese Academy of Sciences, Beijing, China
|
| 英文摘要: | Phrase orders influence much on translation quality. However, general phrase based methods take only the source side information for phrase orderings. We instead propose a bilingual parse structure, Flattened Bilingual Parse Tree (FBPT), for better describing the inner structure of bilingual sentences and then for better translations. The main idea is to extract phrase pairs with orientation features under the help of FBPT structure. Such features can help maintain better sentence generations during translation. Furthermore, the FBPT structure can be learned automatically from parallel corpus with lower costs without the need of complex linguistic parsing. Evaluations on MT08 translation task indicate that 7% relative improvement on BLEU can be achieved compared to distortion based method (like Pharaoh). ©2010 IEEE. |
| 内容类型: | 会议论文
|
| URI标识: | http://ir.iscas.ac.cn/handle/311060/8798
|
| Appears in Collections: | 基础软件国家工程研究中心_会议论文
|
| File Name/ File Size |
Content Type |
Version |
Access |
License |
|
|---|
| 05587836.pdf（1474KB） | -- | -- | 限制开放 | -- | 联系获取全文 |
|
| Recommended Citation: | |
Zhang Dakun,Sun Le,Li Wenbo. improving phrase-based smt model with flattened bilingual parse tree[C]. 见:6th International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2010. Beijing, China. August 21,.
|
|
|
