Sciweavers

1527 search results - page 30 / 306
» Hidden word statistics
Sort
View
ACL
2011
14 years 3 months ago
Semi-supervised Relation Extraction with Large-scale Word Clustering
We present a simple semi-supervised relation extraction system with large-scale word clustering. We focus on systematically exploring the effectiveness of different cluster-based ...
Ang Sun, Ralph Grishman, Satoshi Sekine
IJCAI
2007
15 years 1 months ago
Dynamically Weighted Hidden Markov Model for Spam Deobfuscation
Spam deobfuscation is a processing to detect obfuscated words appeared in spam emails and to convert them back to the original words for correct recognition. Lexicon tree hidden M...
Seunghak Lee, Iryoung Jeong, Seungjin Choi
ACL
2012
13 years 2 months ago
Enhancing Statistical Machine Translation with Character Alignment
The dominant practice of statistical machine translation (SMT) uses the same Chinese word segmentation specification in both alignment and translation rule induction steps in buil...
Ning Xi, Guangchao Tang, Xinyu Dai, Shujian Huang,...
ACL
2009
14 years 9 months ago
Bridging Morpho-Syntactic Gap between Source and Target Sentences for English-Korean Statistical Machine Translation
Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessar...
Gum-Won Hong, Seung-Wook Lee, Hae-Chang Rim
NAACL
2003
15 years 1 months ago
Unsupervised methods for developing taxonomies by combining syntactic and statistical information
This paper describes an unsupervised algorithm for placing unknown words into a taxonomy and evaluates its accuracy on a large and varied sample of words. The algorithm works by ï...
Dominic Widdows