Abstract | We propose Bilingual Tree Kernels (BTKs) to capture the structural similarities across a pair of syntactic translational equivalences and apply BTKs to subtree alignment along with some plain features. |
Abstract | Our study reveals that the structural features embedded in a bilingual parse tree pair are very effective for subtree alignment and the bilingual tree kernels can well capture such features. |
Bilingual Tree Kernels | 2.1 Independent Bilingual Tree Kernel (iBTK) |
Bilingual Tree Kernels | In order to compute the dot product of the feature vectors in the exponentially high dimensional feature space, we introduce the tree kernel functions as follows: |
Bilingual Tree Kernels | The iBTK is defined as a composite kernel consisting of a source tree kernel and a target tree kernel which measures the source and the target structural similarity respectively. |
Introduction | Alternatively, convolution parse tree kernels (Collins and Duffy, 2001), which implicitly explore the tree structure information, have been successfully applied in many NLP tasks, such as Semantic parsing (Moschitti, 2004) and Relation Extraction (Zhang et al. |
Introduction | In multilingual tasks such as machine translation, tree kernels are seldom applied. |
Introduction | In this paper, we propose Bilingual Tree Kernels (BTKs) to model the bilingual translational equivalences, in our case, to conduct subtree alignment. |
Abstract | In this paper we propose using tree kernel based approach to automatically mine the syntactic information from the parse trees for discourse analysis, applying kernel function to the tree structures directly. |
Abstract | The experiment shows tree kernel approach is able to give statistical significant improvements over flat syntactic path feature. |
Abstract | We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further incorporate information from a higher dimension space for possible better discrimination. |
Introduction | In this paper we propose using tree kernel based method to automatically mine the syntactic |
Introduction | The experiment shows that tree kernel is able to effectively incorporate syntactic structural information and produce statistical significant improvements over flat syntactic path feature for the recognition of both explicit and implicit relation in Penn Discourse Treebank (PDTB; Prasad et al., 2008). |
Introduction | We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further work on a higher dimensional space for possible better discrimination. |
Related Work | Tree Kernel based Approach in NLP. |
Related Work | While the feature based approach may not be able to fully utilize the syntactic information in a parse tree, an alternative to the feature-based methods, tree kernel methods (Haussler, 1999) have been proposed to implicitly explore features in a high dimensional space by employing a kernel function to calculate the similarity between two objects directly. |
Related Work | Other sub-trees beyond 2-level (e. g. Tf- 7}) are only captured in the tree kernel, which allows tree kernel to further leverage on information from higher dimension space for possible better discrimination. |