Sciweavers

1527 search results - page 74 / 306
» Hidden word statistics
Sort
View
EMNLP
2010
14 years 11 months ago
It Depends on the Translation: Unsupervised Dependency Parsing via Word Alignment
We reveal a previously unnoticed connection between dependency parsing and statistical machine translation (SMT), by formulating the dependency parsing task as a problem of word a...
Samuel Brody
COLING
2010
14 years 8 months ago
Word Sense Disambiguation-based Sentence Similarity
Previous works tend to compute the similarity between two sentences based on the comparison of their nearest meanings. However, the nearest meanings do not always represent their ...
ChukFong Ho, Masrah Azrifah Azmi Murad, Rabiah Abd...
FCCM
2008
IEEE
112views VLSI» more  FCCM 2008»
15 years 8 months ago
Power-Aware and Branch-Aware Word-Length Optimization
Power reduction is becoming more important as circuit size increases. This paper presents a tool called PowerCutter which employs accuracy-guaranteed word-length optimization to r...
William G. Osborne, José Gabriel F. Coutinh...
IJCNLP
2005
Springer
15 years 7 months ago
Automatic Term Extraction Based on Perplexity of Compound Words
Many methods of term extraction have been discussed in terms of their accuracy on huge corpora. However, when we try to apply various methods that derive from frequency to a small ...
Minoru Yoshida, Hiroshi Nakagawa
EMNLP
2007
15 years 2 months ago
Exploiting Multi-Word Units in History-Based Probabilistic Generation
We present a simple history-based model for sentence generation from LFG f-structures, which improves on the accuracy of previous models by breaking down PCFG independence assumpt...
Deirdre Hogan, Conor Cafferkey, Aoife Cahill, Jose...