Sciweavers

1018 search results - page 114 / 204
» Document Representation in Natural Language Text Retrieval
Sort
View
MMSP
2008
IEEE
159views Multimedia» more  MMSP 2008»
15 years 11 months ago
A text segmentation based approach to video shot boundary detection
Abstract—Video shot boundary detection is one of the fundamental tasks of video indexing and retrieval applications. Although many methods have been proposed for this task, find...
Duy-Dinh Le, Shin'ichi Satoh, Thanh Duc Ngo, Duc A...
EMNLP
2010
15 years 2 months ago
Negative Training Data Can be Harmful to Text Classification
This paper studies the effects of training data on binary text classification and postulates that negative training data is not needed and may even be harmful for the task. Tradit...
Xiaoli Li, Bing Liu, See-Kiong Ng
ACL
2009
15 years 2 months ago
Distributional Representations for Handling Sparsity in Supervised Sequence-Labeling
Supervised sequence-labeling systems in natural language processing often suffer from data sparsity because they use word types as features in their prediction tasks. Consequently...
Fei Huang, Alexander Yates
DOCENG
2004
ACM
15 years 10 months ago
Querying XML documents by dynamic shredding
With the wide adoption of XML as a standard data representation and exchange format, querying XML documents becomes increasingly important. However, relational database systems co...
Hui Zhang 0003, Frank Wm. Tompa
TSD
2010
Springer
15 years 2 months ago
Comparison of Different Lemmatization Approaches through the Means of Information Retrieval Performance
This paper presents a quantitative performance analysis of two different approaches to the lemmatization of the Czech text data. The first one is based on manually prepared diction...
Jakub Kanis, Lucie Skorkovská