Sciweavers

183 search results - page 12 / 37
» Language resources extracted from Wikipedia
Sort
View
98
Voted
SIGIR
2008
ACM
14 years 9 months ago
Enhancing text clustering by leveraging Wikipedia semantics
Most traditional text clustering methods are based on "bag of words" (BOW) representation based on frequency statistics in a set of documents. BOW, however, ignores the ...
Jian Hu, Lujun Fang, Yang Cao, Hua-Jun Zeng, Hua L...
LREC
2008
129views Education» more  LREC 2008»
14 years 11 months ago
Named Entity WordNet
This paper presents the automatic extension of Princeton WordNet with Named Entities (NEs). This new resource is called Named Entity WordNet. Our method maps the noun is-a hierarc...
Antonio Toral, Rafael Muñoz, Monica Monachi...
LREC
2008
112views Education» more  LREC 2008»
14 years 11 months ago
Automatic Acquisition of Usage Information for Language Resources
Recently, language resources (LRs) are becoming indispensable for linguistic research. Unfortunately, it is not easy to find their usages by searching the web even though they mus...
Shunsuke Kozawa, Hitomi Tohyama, Kiyotaka Uchimoto...
SIGIR
2009
ACM
15 years 4 months ago
Web-derived resources for web information retrieval: from conceptual hierarchies to attribute hierarchies
A weakly-supervised extraction method identifies concepts within conceptual hierarchies, at the appropriate level of specificity (e.g., Bank vs. Institution), to which attribute...
Marius Pasca, Enrique Alfonseca
INLG
2010
Springer
14 years 7 months ago
Extracting Parallel Fragments from Comparable Corpora for Data-to-text Generation
Building NLG systems, in particular statistical ones, requires parallel data (paired inputs and outputs) which do not generally occur naturally. In this paper, we investigate the ...
Anja Belz, Eric Kow