Convolution Kernels for Natural Language

By Michael Collins, Nigel P. Duffy. Neural Information Processing Systems, 2001

935 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e6c7adc28e20d361d5c35aa9808094b10f6a34d1

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

Citations in the corpus

Marginalized Kernels Between Labeled Graphs (2003, background): “Watkins (2000), Lodhi et al. (2002), Collins and Duy (2001) , Kashima and Koyanagi (2002)).”
Have You Lost the Thread? Discovering Ongoing Conversations in Scattered Dialog Blocks (2017, background): “In contrast, learning with tree kernels (Collins and Duffy 2001) as well as convolution kernels (Haussler 1999) in general is intractable within the setting of our task.”
Fast Kernels for String and Tree Matching (2002, methodology): “Common examples include biological sequence analysis where data is represented as strings [4] and Natural Language Processing (NLP) where the data is in the form a parse tree [3].”
Bhattacharyya and Expected Likelihood Kernels (2003, background): “For instance, string kernels and sequential data kernels [18, 17, 6, 7, 26, 25] do not specifically address the generative hidden Markov model (HMM) literature.”
Kernel methods in machine learning (2007, neutral): “ll degree of this kernel is p 1p 2, the ﬁrst factor p 1 only captures short range interactions. Tree kernels. We now discuss similarity measures on more structured objects. For trees Collins and Duﬀy [31] proposea decomposition method which maps a tree xinto its set of subtrees. The kernel between t”
Bridging semantics and syntax with graph algorithms - state-of-the-art of extracting biomedical relations (2017, methodology): “Shared resources for biomedical relation extraction Utility category Data sources Terminology/Ontology/Knowledge Base GO [161], UMLS [58], MeSH [162], Wordnet [118], Verbnet [163], Biothesaurus [122], PDB [101], Uniprot [121], SIDER [164], DrugBank [165], HIVDB [166], RegaDB [167], Entrez Gene [153]”
Feature Selection via Dependence Maximization (2012, background): “…samples (x, y): these may be real valued , vector valued, class labels, strings (Lodhi et al., 2002), graphs (Gärtner et al., 2003), dynamical systems (Vishwanathan et al., 2007), parse trees (Collins and Duffy, 2001), images (Schölkopf, 1997), and any other domain on which kernels can be defined.”
Graph kernels and Gaussian processes for relational reinforcement learning (2006, background): “Tree kernels [3] can be applied to ordered trees where the number of children of a node is determined by the label of the node.”
Least-squares two-sample test (2011, background): “Recently, a novel idea of using the universal RKHS (or the Gaussian widths) yielding the maximum MMD value has been introduced (Sriperumbudur et al., 2009).”
Combating Fake News (2019, methodology): “[63] proposed to compare the similarity between propagation trees using tree kernels that were applied to syntactic modeling tasks in [21, 70, 127].”
Text mining for market prediction: A systematic review (2014, methodology): “In the parse-tree method which is based on syntactic structure, a pattern is extracted from the tree of a document by considering not only the word occurrence but also the word sequence in the document (Collins & Duffy, 2001).”
From sample similarity to ensemble similarity: probabilistic distance measures in reproducing kernel Hilbert space (2006, background): “For example, alternative representations include strings [14], graphs [15], lattices [16], statistical manifolds [17], [18], [19], and so on [20], [21].”
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms (2002, background): “See (Collins and Duffy 2001; Collins and Duffy 2002; Collins 2002) for other applications of the voted perceptron to NLP problems.”