268 search results - page 6 / 54 » Improving IBM Word Alignment Model 1 |
140
Voted
NAACL
2010
15 years 1 months ago
2010
Syntactic machine translation systems extract rules from bilingual, word-aligned, syntactically parsed text, but current systems for parsing and word alignment are at best cascade...
124
Voted
ICASSP
2010
IEEE
15 years 3 months ago
2010
IEEE
This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
146
click to vote
ICASSP
2010
IEEE
15 years 1 months ago
2010
IEEE
We investigate incremental word learning with few training examples in a Hidden Markov Model (HMM) framework suitable for an interactive learning scenario with little prior knowle...
122
click to vote
EMNLP
2007
15 years 4 months ago
2007
Word alignment is the problem of annotating parallel text with translational correspondence. Previous generative word alignment models have made structural assumptions such as the...
147
click to vote
ACL
2008
15 years 4 months ago
2008
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...