287 search results - page 37 / 58 » Mixing Multiple Translation Models in Statistical Machine Tr... |
LREC
2010
14 years 11 months ago
2010
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...
81
Voted
LREC
2008
14 years 11 months ago
2008
Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual a...
ACL
2008
14 years 11 months ago
2008
This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and ...
ACL
2007
14 years 11 months ago
2007
Recently, confusion network decoding has been applied in machine translation system combination. Due to errors in the hypothesis alignment, decoding may result in ungrammatical co...
COLING
2002
14 years 9 months ago
2002
I present a novel approach to the determination of recurrent sound correspondences in bilingual wordlists. The idea is to relate correspondences between sounds in wordlists to tra...