NAACL
2010
14 years 27 days ago
2010
We describe a class of translation model in which a set of input variants encoded as a context-free forest is translated using a finitestate translation model. The forest structur...
MT
2010
14 years 1 months ago
2010
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
CIKM
2010
Springer
14 years 1 months ago
2010
Springer
Web search is challenging partly due to the fact that search queries and Web documents use different language styles and vocabularies. This paper provides a quantitative analysis ...
IPM
2007
14 years 2 months ago
2007
In the KL divergence framework, the extended language modeling approach has a critical problem estimating a query model, which is the probabilistic model that encodes user’s inf...
ACL
2000
14 years 4 months ago
2000
I describe two methods for incorporating information about the relative positions of bilingual word pairs into a Maximum Entropy/Minimum Divergence translation model. The better o...
ACL
1998
14 years 4 months ago
1998
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
ACL
2003
14 years 4 months ago
2003
This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first per...
EMNLP
2004
14 years 4 months ago
2004
We describe experiments carried out with adaptive language and translation models in the context of an interactive computer-assisted translation program. We developed cache-based ...
NAACL
2007
14 years 4 months ago
2007
This paper presents a maximum entropy machine translation system using a minimal set of translation blocks (phrase-pairs). While recent phrase-based statistical machine translatio...
EMNLP
2007
14 years 4 months ago
2007
We present a method for improving word alignment for statistical syntax-based machine translation that employs a syntactically informed alignment model closer to the translation m...