We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Improving syntactic rule extraction through deleting spurious links with translation span alignment.
- Authors
ZHU, JINGBO; LI, QIANG; XIAO, TONG
- Abstract
Most statistical machine translation systems typically rely on word alignments to extract translation rules. This approach would suffer from a practical problem that even one spurious word alignment link can prevent some desirable translation rules from being extracted. To address this issue, this paper presents two approaches, referred to as sub-tree alignment and phrase-based forced decoding methods, to automatically learn translation span alignments from parallel data. Then, we improve the translation rule extraction by deleting spurious links and inserting new links based on bilingual translation span correspondences. Some comparison experiments are designed to demonstrate the effectiveness of the proposed approaches.
- Subjects
FRAMES (Linguistics); RULE extraction (Machine learning); DELETION (Linguistics); TRANSLATING &; interpreting; PHONOLOGICAL decoding
- Publication
Natural Language Engineering, 2015, Vol 21, Issue 2, p227
- ISSN
1351-3249
- Publication type
Article
- DOI
10.1017/S1351324913000260