Improving syntactic rule extraction through deleting spurious links with translation span alignment
2013 ◽
Vol 21
(2)
◽
pp. 227-249
◽
Keyword(s):
AbstractMost 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.
2013 ◽
Vol 48
◽
pp. 733-782
◽
2016 ◽
Vol 22
(4)
◽
pp. 549-573
◽
2012 ◽
Vol 97
(1)
◽
pp. 43-53
2010 ◽
Vol 36
(2)
◽
pp. 247-277
◽
2016 ◽
Vol 106
(1)
◽
pp. 125-146
◽
2017 ◽
Vol 37
(5)
◽
pp. 307
2017 ◽
Vol 37
(5)
◽
pp. 307
Keyword(s):