Sciweavers

6 search results - page 1 / 2
» Convolution Kernel over Packed Parse Forest
Sort
View
ACL
2010
13 years 1 months ago
Convolution Kernel over Packed Parse Forest
This paper proposes a convolution forest kernel to effectively explore rich structured features embedded in a packed parse forest. As opposed to the convolution tree kernel, the p...
Min Zhang, Hui Zhang, Haizhou Li
ACL
2008
13 years 5 months ago
Forest Reranking: Discriminative Parsing with Non-Local Features
Conventional n-best reranking techniques often suffer from the limited scope of the nbest list, which rules out many potentially good alternatives. We instead propose forest reran...
Liang Huang
ACL
2009
13 years 1 months ago
Improving Tree-to-Tree Translation with Packed Forests
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...
Yang Liu, Yajuan Lü, Qun Liu
IPM
2008
159views more  IPM 2008»
13 years 3 months ago
Exploring syntactic structured features over parse trees for relation extraction using kernel methods
Extracting semantic relationships between entities from text documents is challenging in information extraction and important for deep information processing and management. This ...
Min Zhang, Guodong Zhou, AiTi Aw
NIPS
2001
13 years 5 months ago
Convolution Kernels for Natural Language
We describe the application of kernel methods to Natural Language Processing (NLP) problems. In many NLP tasks the objects being modeled are strings, trees, graphs or other discre...
Michael Collins, Nigel Duffy