Syntactic N-grams as machine learning features for natural language processing
Expert Systems with ApplicationsPublished 22 August 2013
Grigori Sidorov, Francisco Velásquez, Efstathios Stamatatos, Alexander Gelbukh, Liliana Chanona-Hernández
Citations319
SJR quartileQ1
SJR score1.85
SNIP2.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Sn-grams can be applied in any natural language processing (NLP) task where traditional n- grams are used and described how sn-rams were applied to authorship attribution.
Abstract
In this paper we introduce and discuss a concept of syntactic n-grams (sn-grams). Sn-grams differ from traditional n-grams in the manner how we construct them, i.e., what elements are considered neighbors. In case of sn-grams, the neighbors are taken by following syntactic relations in syntactic trees, and not by taking words as they appear in a text, i.e., sn-grams are constructed by following paths in syntactic trees. In this manner, sn-grams allow bringing syntactic knowledge into machine learning methods; still, previous parsing is necessary for their construction. Sn-grams can be applied in any natural language processing (NLP) task where traditional n-grams are used. We describe how sn-grams were applied to authorship attribution. We used as baseline traditional n-grams of words, part of speech (POS) tags and characters; three classifiers were applied: support vector machines (SVM), naive Bayes (NB), and tree classifier J48. Sn-grams give better results with SVM classifier.
Keywords
Computer Science
ACM SIGKDD Explorations NewsletterThe WEKA data mining software
17,849 Citations2009Mark Hall, Eibe Frank +4 more
This paper provides an introduction to the WEKA workbench, reviews the history of the project, and, in light of the recent 3.6 stable release, briefly discusses what has been added since the last stable version (Weka 3.4) released in 2003.
ACM Computing SurveysMachine learning in automated text categorization
7,899 Citations2002Fabrizio Sebastiani
This survey discusses the main approaches to text categorization that fall within the machine learning paradigm and discusses in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation.
Generating Typed Dependency Parses from Phrase Structure Parses
2,304 Citations2006Marie-Catherine de Marneffe, Bill MacCartney +1 more
A system for extracting typed dependency parses of English sentences from phrase structure parses that captures inherent relations occurring in corpus texts that can be critical in real-world applications is described.
Journal of the American Society for Information Science and TechnologyA survey of modern authorship attribution methods
1,137 Citations2008Efstathios Stamatatos
Authorship attribution supported by statistical or computational methods has a long history starting from the 19th century and is marked by the seminal study of Mosteller and Wallace (1964) on the effects of EMMARM on authorship attribution.
Foundations and Trends® in Information RetrievalAuthorship Attribution
479 Citations2008Patrick Juola
This review shows that the authorship attribution discipline is quite successful, even in difficult cases involving small documents in unfamiliar and less studied languages; it further analyzes the types of analysis and features used and tries to determine characteristics of well-performing systems, finally formulating these in a set of recommendations for best practices.
Literary and Linguistic ComputingThe Evolution of Stylometry in Humanities Scholarship
471 Citations1998David I. Holmes
The growing power of the computer and the ready availability of machine-readable texts are transforming modern stylometry, which has now attracted the attention of the media.
Literary and Linguistic ComputingQuantitative Authorship Attribution: An Evaluation of Techniques
424 Citations2007John Grieve
A comparison of thirty-nine different types of textual measurements commonly used in attribution studies is presented, in order to determine which are the best indicators of authorship.
IEEE Intelligent SystemsApplying Authorship Analysis to Extremist-Group Web Forum Messages
398 Citations2005Ahmed Abbasi, Hsinchun Chen
A special multilingual model is developed - the set of algorithms and related features - to identify Arabic messages, gearing this model toward the language's unique characteristics and incorporated a complex message extraction component to allow the use of a more comprehensive set of features tailored specifically toward online messages.
Literary and Linguistic ComputingOutside the cave of shadows: using syntactic annotation to enhance authorship attribution
387 Citations1996R. Harald Baayen, Hans van Halteren +1 more
The outcome of this experimentests that the frequencies with which syntactic rewrite rules are put to use provide a better clue to authorship than word usage.
N-GRAM-BASED AUTHOR PROFILES FOR AUTHORSHIP ATTRIBUTION
382 Citations2003Vlado Ke, Fuchun Peng +2 more
This work presents a novel method for computer-assisted authorship attribution based on characterlevel n-gram author proles, which is motivated by an almost-forgotten, pioneering method in 1976.
Applied IntelligenceAuthorship Attribution with Support Vector Machines
339 Citations2003Joachim Diederich, Jörg Kindermann +2 more
The support vector machine (SVM) is applied to the use of text-mining methods for the identification of the author of a text, as it is able to cope with half a million of inputs it requires no feature selection and can process the frequency vector of all words of atext.
Language Resources and EvaluationAuthorship attribution in the wild
303 Citations2010Moshe Koppel, Jonathan Schler +1 more
This paper shows the precise relationship between attribution precision and four parameters: the size of the candidate set, the quantity of known-text by the candidates, the length of the anonymous text and a certain robustness score associated with a attribution.
A Closer Look at Skip-gram Modelling
261 Citations2006David Guthrie, Ben Allison +3 more
The amount of extra training data required to achieve skip-gram coverage using standard adjacent tri-grams is determined, which is determined by computing all possible skip-rams in a training corpus and measuring how many adjacent (standard) n- grams these cover in test documents.
Journal of Machine Learning ResearchMeasuring Differentiability: Unmasking Pseudonymous Authors
182 Citations2007Moshe Koppel, Jonathan Schler +1 more
Contextual phrase-level polarity analysis using lexical affect scoring and syntactic N-grams
177 Citations2009Apoorv Agarwal, Fadi Biadsy +1 more
A classifier is presented to predict contextual polarity of subjective phrases in a sentence using lexical scoring derived from the Dictionary of Affect in Language and extended through WordNet and n-gram analysis to capture the effect of context.
Local Histograms of Character N-grams for Authorship Attribution
107 Citations2011Hugo Jair Escalante, Thamar Solorio +1 more
It is shown that LHs are particularly helpful for AA, because they provide useful information for uncovering, to some extent, the writing style of authors for related tasks, such as authorship verification and plagiarism detection.
Lecture notes in computer scienceSyntactic Dependency-Based N-grams as Classification Features
103 Citations2013Grigori Sidorov, Francisco Velásquez +3 more
It is described how sn-grams were applied to authorship attribution, and how SVM classifier for several profile sizes was used, which resulted in better results.
Journal of Machine Learning ResearchMeasuring Differentiability: Unmasking Pseudonymous Authors
102 Citations2007KoppelMoshe, SchlerJonathan +1 more
A new learning-based method for adducing the "depth of difference" between two example sets is presented and evidence that this method solves the authorship verification problem with very high accuracy is offered.
ACM Transactions on Speech and Language ProcessingAuthor verification by linguistic profiling
92 Citations2007Hans van Halteren
The effects of parameter settings in linguistic profiling, a technique in which large numbers of counts of linguistic features are used as a text profile which can then be compared to average profiles for groups of texts, are explored.
Overview of the International Authorship Identification Competition at PAN-2011.
54 Citations2011Shlomo Argamon, Patrick Juola
An overview of the evaluation methodology applied to authorship identication solutions as part of PAN 2011 is given, which summarizes the methods used by the various participants, which were quite varied, and presents the overall results.
Finding Maximal Sequential Patterns in Text Document Collections and Single Documents
29 Citations2010René Arnulfo García-Hernández, José Fco. Martínez-Trinidad +1 more
Two algorithms for discovering all the Maximal Sequential Patterns (MSP) in a document collection and in a single document are presented following the “pattern-growth strategy” where small frequent sequences are found first with the goal of growing them to obtain MSP.
Lecture notes in computer scienceThe Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation
28 Citations2004Nizar Habash
A statistical structural N-gram model is used in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system for lexical and structural selection and shows that it decreases runtime by 60% with no loss in translation quality.
Lecture notes in computer scienceSyntactic Dependency-Based N-grams: More Evidence of Usefulness in Classification
26 Citations2013Grigori Sidorov, Francisco Velásquez +3 more
This paper applied sn-grams in the task of authorship attribution for corpora of three and seven authors with very promising results.
N-gram-based statistical machine translation versus syntax augmented machine translation
18 Citations2009Maxim Khalilov, José A. R. Fonollosa
This paper provides a step-by-step comparison of the systems and reports results in terms of automatic evaluation metrics and required computational resources for a smaller Arabic-to-English translation task (1.5M tokens in the training corpus).