Text Classification using String Kernels

By Huma Mahmood Lodhi, John Shawe-Taylor, Nello Cristianini, Christopher J. C. H. Watkins. Neural Information Processing Systems, 2000

310 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a657cdfb3937c27ee520bbc4d4cd8dc7f5f65ae4

How researchers see this paper

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

Citations in the corpus

A brief survey on sequence classification (2010, methodology): “SVM has been proved to be an eﬀective method for sequence classiﬁcation [43; 39; 35; 54; 55; 52; 13].”
Learning with Kernels: support vector machines, regularization, optimization, and beyond (2001, unknown): “• kernel design – transformation invariances [13] – kernels for discrete objects [30, 78, 40, 18, 74] – kernels based on generative models [34, 61, 68] – local kernels [e.”
Learning Language Semantics from Ambiguous Supervision (2007, methodology): “Specifically, we add an iterative retraining method to KRISP (Kate & Mooney 2006), a system that learns a semantic parser using a support-vector machine (SVM) that utilizes a string kernel (Lodhi et al. 2002).”
Expressivity versus efficiency of graph kernels (2003, background): “In order to control the complexity of such kernels, one line of existing research has concentrated on special kinds of graphs, in particular, trees [2] or strings [11, 9] which results in eﬃcient kernels, but loses most of the power of general graphs.”
Training RNNs as Fast as CNNs (2017, background): “Lei et al. (2017) demonstrate that a broad model class (including SRU and word-level CNNs) can been seen as embedding sequence similarity functions such string kernels (Lodhi et al., 2002) into hidden space.”
Towards Understanding Gender Bias in Relation Extraction (2019, methodology): “…categorized as supervised, including feature-based methods (Kambhatla, 2004; Zhou et al., 2005; Zhao and Grishman, 2005) and kernel-based methods (Lodhi et al., 2002; Zelenko et al., 2003), or semi-supervised (Brin, 1998; Agichtein and Gravano, 2000; Etzioni et al., 2005; Pantel and…”
Graph-based term weighting for text categorization (2015, unknown): “…related work on TC, graph-based TC methods and graph-based techniques in text mining and IR. a) Text classiﬁcation: TC is one of the most fundamental and well studied tasks in text analytics and a number of diverse approaches have been proposed [21], [35], [14], [15], [22], [37], [26], [16], [19].”
Neural methods for non-standard data (2004, background): “Thereby, the approaches differ with respect to the weighting of matches, whether partial matches are allowed, and whether substrings need to be contiguous [59, 63].”
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes (2015, methodology): “For each production, an SVM classiﬁer is trained using a string subsequence kernel (Lodhi et al., 2002).”
Discriminative Frequent Pattern Analysis for Effective Classification (2007, methodology): “Non-linear mapping is widely used, e.g. , string kernel [15, 12] for text or biosequence clas-siﬁcation.”
Effective Pattern Discovery for Text Mining (2012, methodology): “Since the works of Joachims [15], [16], researchers have successfully applied SVM to many related tasks and presented some convincing results [5], [6], [27], [39], [55].”
Knowing what you know: valid confidence sets in multiclass and multilabel prediction (2020, background): “For example, in object detection problems [26, 30, 22], we want to detect several entities in an image, while in text classiﬁcation tasks [23, 24, 17], a single document can potentially share multiple topics.”
Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning (2008, methodology): “We randomly divided the data from the 1,000 images into a learning set (650) and a test set (350).”
Distributional Word Clusters vs. Words for Text Categorization (2003, background): “, 2000), “string kernels” (Lodhi et al., 2002) and even representations based on word clusters (Baker and McCallum, 1998), the simple minded independent word-based representation, known as Bag-Of-Words (BOW), remained very popular.”
Knowing what You Know: valid and validated confidence sets in multiclass and multilabel prediction (2020, background): “…in object detection problems (Redmon et al., 2016; Tan et al., 2019; Lin et al., 2014), we wish to detect several entities in an image, while in text classiﬁcation tasks (Lodhi et al., 2002; McCallum and Nigam, 1998; Joulin et al., 2016), a single document can potentially share multiple topics.”
Text Classification using String Kernels (2002, result): “This paper builds on preliminary results present in Lodhi et al. (2001).”
Language Identification: The Long and the Short of the Matter (2010, unknown): “…vector machines (SVMs) and kernel methods have been applied to the task of language identiﬁcation task with success (Teytaud and Jalam, 2001; Lodhi et al., 2002; Kruengkrai et al., 2005), and Markov logic has been used for joint in-ferencing in contexts where there are multiple evidence…”