Using N-gram and Word Network Features for Native Language Identification
Published 1 June 2013
Shibamouli Lahiri, Rada Mihalcea
Citations8
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
Experiments show that word networks have competitive performance against the baseline feature set in the Native Language Identification Shared Task, which is a promising result.
Abstract
We report on the performance of two different feature sets in the Native Language Identification Shared Task (Tetreault et al., 2013). Our feature sets were inspired by existing literature on native language identification and word networks. Exper-iments show that word networks have competitive performance against the baseline feature set, which is a promising result. We also present a discussion of feature analysis based on information gain, and an overview on the performance of different word net-work features in the Native Language Identification task.
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.
Empirical Methods in Natural Language ProcessingTextRank: Bringing Order into Text
3,347 Citations2004Rada Mihalcea, Paul Tarau
TextRank, a graph-based ranking model for text processing, is introduced and it is shown how this model can be successfully used in natural language applications.
Proceedings of the Royal Society B Biological SciencesThe small world of human language
1,040 Citations2001Ramon Ferrer‐i‐Cancho, Ricard V. Solé
It is shown that graphs of words in sentences display two important features recently found in a disparate number of complex systems, the so called small–world effect and a scale–free distribution of degrees.
arXiv (Cornell University)An O(m) Algorithm for Cores Decomposition of Networks
624 Citations2003Vladimir Batagelj, Matjaž Zaveršnik
An algorithm for determining the cores decomposition of a given simple network, based on k{cores, proposed in 1983 by Seidman, and an application on the authors collaboration network in computational geometry is presented.
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.
ETS Research Report SeriesTOEFL11: A CORPUS OF NON‐NATIVE ENGLISH
200 Citations2013Daniel Blanchard, Joel Tetreault +3 more
A new corpus of non-native English writing will be useful for the task of native language identification, as well as grammatical error detection and correction, and automatic essay scoring.
Determining an author's native language by mining a text for errors
167 Citations2005Moshe Koppel, Jonathan Schler +1 more
It is shown that stylistic text features can be exploited to determine an anonymous author's native language with high accuracy and serve as features for support vector machines that learn to classify texts according to author native language.
A Report on the 2017 Native Language Identification Shared Task
158 Citations2017Shervin Malmasi, Keelan Evanini +6 more
The fusion track showed that combining the written and spoken responses provides a large boost in prediction accuracy, and multiple classifier systems were the most effective in all tasks, with most based on traditional classifiers with lexical/syntactic features.
An O(m) Algorithm for Cores Decomposition of Networks
101 Citations2003Vladimir Batagelj
North American Chapter of the Association for Computational LinguisticsStylometric Analysis of Scientific Articles
88 Citations2012Shane Bergsma, Matt Post +1 more
Exploiting Parse Structures for Native Language Identification
77 Citations2011Sze-Meng Jojo Wong, Mark Dras
This paper takes two types of parse substructure as features---horizontal slices of trees, and the more general feature schemas from discriminative parse reranking---and shows that using this kind of syntactic feature results in an accuracy score in classification of seven native languages of around 80%, an error reduction of more than 30%.
Contrastive Analysis and Native Language Identification
65 Citations2009Sze-Meng Jojo Wong, Mark Dras
This preliminary study provides some support for the use of this kind of syntactic errors as a clue to identifying the native language of an author.
Native Language Detection with Tree Substitution Grammars
50 Citations2012Benjamin Swanson, Eugene Charniak
This work investigates the potential of Tree Substitution Grammars as a source of features for native language detection, the task of inferring an author's native language from text in a different language.
Native language detection with 'cheap' learner corpora
48 Citations2013Julian Brooke, Graeme Hirst
The web-scraped Lang-8 learner corpus is presented, and it is useful for the task, particularly if large quantities of data are used, and seems to facilitate the use of lexical features, which have been previously avoided.
TAT: An Author Profiling Tool with Application to Arabic Emails
43 Citations2007Dominique Estival, Tanja Gaustad +3 more
The overall TAT system and the Machine Learning experiments resulting in classifiers for the different author traits are described and predictions for demographic and psychometric author traits show improvements over the baseline for some of the author traits.
Approaching language transfer through text classification : explorations in the detection-based approach
41 Citations2012Scott Jarvis, Scott A. Crossley
Robust, Lexicalized Native Language Identification
40 Citations2012Julian Brooke, Graeme Hirst
This work demonstrates the efficacy of lexical features, which had previously been avoided due to the within-corpus topic confounds, and presents strong evidence calling into question the validity of cross- validation evaluation using the standard dataset.
Lecture notes in computer scienceA Document as a Small World
34 Citations2001Yutaka Matsuo, Yukio Ohsawa +1 more
This paper shows that the network has the characteristics of being small world, i.e., highly clustered and short path length, and based on the topology, can extract important terms, even if they are rare, by measuring their contribution to the graphBeing small world.
International Conference on Computational LinguisticsNative Language Identification using Recurring $n$-grams -- Investigating Abstraction and Domain Dependence
33 Citations2012Serhiy Bykh, Detmar Meurers
This paper discusses the systematic use of recurring n-grams of any length as features for training a native language classifier and investigates two degrees of abstraction incorporating parts-of-speech.
Empirical Methods in Natural Language ProcessingExploring Adaptor Grammars for Native Language Identification
32 Citations2012Sze-Meng Jojo Wong, Mark Dras +1 more
This work investigates adaptor grammars' extension to identifying n-gram collocations of arbitrary length over a mix of PoS tags and words, using both maxent and induced syntactic language model approaches to classification.
Measuring Interlanguage: Native Language Identification with L1-influence Metrics
24 Citations2012Julian Brooke, Graeme Hirst
This paper introduces a method for L1 identification in second language (L2) texts that relies only on much more plentiful L1 data, rather than the L2 texts that are traditionally used for training.
Multilingual Matters eBooks4. Detecting the First Language of Second Language Writers Using Automated Indices of Cohesion, Lexical Sophistication, Syntactic Complexity and Conceptual Knowledge
20 Citations2012Scott A. Crossley, Danielle S. McNamara
Topic Modeling for Native Language Identification
14 Citations2011Sze-Meng Jojo Wong, Mark Dras +1 more
This paper looks at the idea of using Latent Dirichlet Allocation as a feature clustering technique over lexical features to see whether there is any evidence that smaller-scale features do cluster into more coherent latent factors, and investigates their effect in a classification task.
Journal of the American Society for Information Science and TechnologyUsing psycholinguistic features for profiling first language of authors
11 Citations2012Rosemary Torney, Peter Vamplew +1 more
It was found that LIWC features were competitive with previously used feature types in identifying the first language of an author, and that combined feature sets including LI WC features consistently showed better accuracy rates and average F measures than were achieved by the same feature sets without the LIWC Features.
Linguistic profiling of texts for the purpose of language verification
6 Citations2004Hans van Halteren, Nelleke Oostdijk
A method to verify automatically that texts are of (near-) native quality and separate native and non-native learner texts for the LOCNESS and ICLE corpora is developed.