46 search results - page 4 / 10 » Clustering Comparable Corpora For Bilingual Lexicon Extracti... |
COLING
2002
13 years 5 months ago
2002
An unsupervised method for word sense disambiguation using a bilingual comparable corpus was developed. First, it extracts statistically significant pairs of related words from th...
ICASSP
2009
IEEE
14 years 8 days ago
2009
IEEE
The major limitation in bilingual latent semantic analysis (bLSA) is the requirement of parallel training corpora. Motivated by semi-supervised learning, we propose a clusterbased...
ECIR
2010
Springer
13 years 7 months ago
2010
Springer
Topic models have been studied extensively in the context of monolingual corpora. Though there are some attempts to mine topical structure from cross-lingual corpora, they require ...
COLING
2000
13 years 6 months ago
2000
This paper proposes a method for extracting bilingual text pairs from a comparable corpus. The basic idea of the method is to apply bootstrapping to an existing corpusbased cross-...
NAACL
2010
13 years 3 months ago
2010
The quality of a statistical machine translation (SMT) system is heavily dependent upon the amount of parallel sentences used in training. In recent years, there have been several...