Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees

By Alessandro Moschitti. 2006

505 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Computational Linguistics & Semantics

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Computational Linguistics & Semantics

Citations in the corpus

Discriminative Neural Sentence Modeling by Tree-Based Convolution (2015, methodology): “Kernel machines, e.g., SVM, are exploited in Moschitti (2006) and Reichartz et al. (2010) by specifying a certain measure of similarity between sentences, without explicit feature representation.”
Ordered Decompositional DAG kernels enhancements (2015, background): “The set of features related to the ST+ kernel is a superset of the features of ST and a subset of the features of PT [15].”
Tree Kernels for Semantic Role Labeling (2008, methodology): “In the next sections, we brieﬂy introduce the kernel trick and describe the subtree (ST) kernel devised in Vishwanathan and Smola (2002), the subset tree (SST) kernel deﬁned in Collins and Duffy (2002), and the partial tree (PT) kernel proposed in Moschitti (2006a).”
Generative Kernels for Tree-Structured Data (2018, methodology): “The Partial Tree kernel (PT) [29] relaxes SST to allow partial productions of the parse-tree grammar, basically allowing to perform partial matching between subtrees at the cost of an increased computational complexity, that is , where L T is the maximum outdegree among the trees.”
A Tree-Based Kernel for Graphs (2012, background): “State of the art results on various benchmark datasets prove the effectiveness of our approach.”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, background): “They categorized kernels into the following categories: (1) shallow linguistic (SL) kernels [140]; (2) constituent parse tree-based kernels, including subtree (ST) [141], subset tree (SST) [142] and partial tree (PT) [143] kernels that use increasingly generalized forms of subtrees, as well as a spe”
Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking (2016, methodology): “The toolkit enables the use of structural kernels (Moschitti, 2006) in SVM-light (Joachims, 2002).”
Translating Questions to SQL Queries with Generative Parsers Discriminatively Reranked (2012, methodology): “To learn the reranker, we used SVM-Light-TK6, which extends the SVM-Light optimizer (Joachims, 1999) with tree kernels (Moschitti, 2006) as described in (Giordani and Moschitti, 2009b).”
Sentiment Analysis of Twitter Data (2011, methodology): “For calculating the similarity between two trees we use a Partial Tree (PT) kernel ﬁrst proposed by Moschitti (2006).”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, methodology): “Most importantly, we deﬁne an innovative and efﬁcient class of kernels, i.e. the Smoothed Partial Tree Kernels (SPTKs), which can measure the similarity of structural similar trees whose nodes are associated with different but re-lated lexicals.”
A Comprehensive Benchmark of Kernel Methods to Extract Protein–Protein Interactions from Literature (2010, methodology): “A bag-of-words kernel, a subset tree kernel [28], and an APG kernel [17] were used together with dependency parses and deep parses.”
Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions (2010, background): “Insert the former root as the last child on the s side of T ( j ) .”
Semantic Matching in Search (2014, result): “Moschitti and Zanzotto [138, 139, 203] define a class of syntactic tree kernels, referred to as tree rewriting kernel in this survey, for paraphrasing and textual entailment, in contrast with conventional”
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning (2017, methodology): “Unlike traditional tree kernel (Moschitti, 2006; Zhang et al., 2008) for modeling syntactic structure based on parse tree, our propagation tree consists of nodes corresponding to microblog”
Semantic Sentiment Analysis of Twitter (2012, methodology): “A partial tree kernel [8] was used to calculate the similarity between two trees.”
Learning Semantic Textual Similarity with Structural Representations (2013, methodology): “F 3 for PTK) computed in all-vs-all mode (-”
ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity (2017, methodology): “Syntactic Parse Features: In order to model tree structured similarity between two sentences rather than sequence-based similarity, inspired by Moschitti (2006), we adopt tree kernels to calculate the similarity between two syntactic parse trees.”