Sciweavers

843 search results - page 161 / 169
» Segmentation of Compressed Documents
Sort
View
63
Voted
LREC
2008
115views Education» more  LREC 2008»
14 years 11 months ago
Experiments on Processing Overlapping Parallel Corpora
The number and sizes of parallel corpora keep growing, which makes it necessary to have automatic methods of processing them: combining, checking and improving corpora quality, et...
Mark Fishel, Heiki Jaan Kaalep
74
Voted
BXML
2004
14 years 11 months ago
Query Reformulation for the XML standards XPath, XQuery and XSLT
: Whenever transformation of data is used to bridge the gap of different data formats, and a query is given in the destination format, query reformulation can speed up the transfor...
Sven Groppe, Stefan Böttcher
NAACL
2003
14 years 11 months ago
Japanese Named Entity Extraction with Redundant Morphological Analysis
Named Entity (NE) extraction is an important subtask of document processing such as information extraction and question answering. A typical method used for NE extraction of Japan...
Masayuki Asahara, Yuji Matsumoto
WCE
2007
14 years 10 months ago
A Fast Multivariate Nearest Neighbour Imputation Algorithm
— Imputation of missing data is important in many areas, such as reducing non-response bias in surveys and maintaining medical documentation. Nearest neighbour (NN) imputation al...
Norman Solomon, Giles Oatley, Kenneth McGarry
69
Voted
ICASSP
2010
IEEE
14 years 10 months ago
Using n-best recognition output for extractive summarization and keyword extraction in meeting speech
There has been increasing interest recently in meeting understanding, such as summarization, browsing, action item detection, and topic segmentation. However, there is very limite...
Yang Liu, Shasha Xie, Fei Liu