Title :
Reordering adverbial chunks in Chinese-English patent machine translation
Author :
Hongzheng Li ; Yun Zhu ; Yang Yang ; Yaohong Jin
Author_Institution :
Inst. of Chinese Inf. Process., Beijing Normal Univ., Beijing, China
Abstract :
Adverbial chunks are widely distributed in Chinese patent document, this paper proposes a rule-based method of reordering long distance adverbial chunks for Chinese-English patent MT system. After analyzing common types of adverbials, different reordering ideas and formal rules are designed for various adverbials according to semantic and expression features of them, as well as systematic differences of word orders between Chinese and English. Related BLEU evaluation scores have improved efficiently compared with baseline, indicating the reordering method was helpful to improve final translation results.
Keywords :
document handling; language translation; law administration; natural language processing; patents; BLEU evaluation scores; Chinese patent document; Chinese-English patent MT system; Chinese-English patent machine translation; formal rules; long distance adverbial chunk reordering; rule-based method; Computational modeling; Google; Organizations; Patents; Pumps; Radio frequency; Syntactics; Adverbial; Machine Translation; Reordering; Rule;
Conference_Titel :
Cloud Computing and Intelligence Systems (CCIS), 2014 IEEE 3rd International Conference on
Print_ISBN :
978-1-4799-4720-1
DOI :
10.1109/CCIS.2014.7175763