Sciweavers

1527 search results - page 57 / 306
» Hidden word statistics
Sort
View
ACL
1997
15 years 1 months ago
Choosing the Word Most Typical in Context Using a Lexical Co-Occurrence Network
This paper presents a partial solution to a component of the problem of lexical choice: choosing the synonym most typical, or expected, in context. We apply a new statistical appr...
Philip Edmonds
EMNLP
2010
14 years 9 months ago
Enhancing Domain Portability of Chinese Segmentation Model Using Chi-Square Statistics and Bootstrapping
Almost all Chinese language processing tasks involve word segmentation of the language input as their first steps, thus robust and reliable segmentation techniques are always requ...
Baobao Chang, Dongxu Han
CORR
2010
Springer
139views Education» more  CORR 2010»
14 years 12 months ago
The semantic mapping of words and co-words in contexts
Meaning can be generated when information is related at a systemic level. Such a system can be an observer, but also a discourse, for example, operationalized as a set of document...
Loet Leydesdorff, Kasper Welbers
TSD
2010
Springer
14 years 10 months ago
Using TectoMT as a Preprocessing Tool for Phrase-Based Statistical Machine Translation
Abstract. We present a systematic comparison of preprocessing techniques for two language pairs: English-Czech and English-Hindi. The two target languages, although both belonging ...
Daniel Zeman
CORR
1999
Springer
59views Education» more  CORR 1999»
14 years 11 months ago
HMM Specialization with Selective Lexicalization
We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. 'Our approach examines the d...
Jin-Dong Kim, Sang-Zoo Lee, Hae-Chang Rim