Structured Lexical Similarity via Convolution Kernels on Dependency Trees

149 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Graph Invariant Kernels (2015, result): “Our result can be compared to the 94.8% obtained by Croce et al. (2011), when they combine kernels on lexical centered trees LCT with a word vector representation obtained with latent semantic analysis.”
Auditing Deep Learning processes through Kernel-based Explanatory Models (2019, methodology): “Consistently with (Croce et al., 2011), in our experiments the KDA has been empowered with a Smoothed Partial Tree Kernel, operating over Grammatical Relation Centered Trees (GRCT) derived from dependency grammar.”
Measuring Word Relatedness Using Heterogeneous Vector Space Models (2012, methodology): “Other than directly applying it to measuring semantic relatedness, our approach is complementary to more sophisticated similarity measures such as developing kernel functions for different structured data (Croce et al., 2011), where the similarity between words serves as a basic component.”
A Structural Smoothing Framework For Robust Graph Comparison (2015, methodology): “Our framework is similar to dependency tree kernels [4] since both methods are using the notion of smoothing for structured objects.”
Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking (2016, methodology): “A straightforward methods for achieving this is to use the Smoothed Partial Tree Kernel by Croce et al. (2011).”