Classifier Stacking for Native Language Identification
This paper reports our contribution (team WLZ) to the NLI Shared Task 2017 (essay track). We first extract lexical and syntactic features from the essays, perform feature weighting and selection, and train linear support vector machine (SVM) classifiers each on an individual feature type. The output of base classifiers, as probabilities for each class, are then fed into a multilayer perceptron to predict the native language of the author. We also report the performance of each feature type, as well as the best features of a type. Our system achieves an accuracy of 86.55{\%}, which is among the best performing systems of this shared task.
Code (0)
등록된 구현이 없습니다.
Tasks
Language AcquisitionLanguage IdentificationNative Language IdentificationText ClassificationVocal Bursts Type PredictionSimilar Papers 제목 키워드 기반
Native Language Identification With Classifier Stacking and Ensembles
Ensemble methods using multiple classifiers have proven to be among the most successful approaches for the task of Native Language Identification (NLI), achieving the current state of the art. However, a systematic exami…
Cross-corpusGeneral ClassificationLanguage AcquisitionLanguage Identification+2Native Language Identification using Stacked Generalization
Ensemble methods using multiple classifiers have proven to be the most successful approach for the task of Native Language Identification (NLI), achieving the current state of the art. However, a systematic examination o…
Language IdentificationNative Language IdentificationLTG-ST at NADI Shared Task 1: Arabic Dialect Identification using a Stacking Classifier
This paper presents our results for the Nuanced Arabic Dialect Identification (NADI) shared task of the Fifth Workshop for Arabic Natural Language Processing (WANLP 2020). We participated in the first sub-task for countr…
Dialect IdentificationregressionNative Language Identification on Text and Speech
This paper presents an ensemble system combining the output of multiple SVM classifiers to native language identification (NLI). The system was submitted to the NLI Shared Task 2017 fusion track which featured students e…
Language IdentificationNative Language IdentificationA Review of Standard Text Classification Practices for Multi-label Toxicity Identification of Online Content
Language toxicity identification presents a gray area in the ethical debate surrounding freedom of speech and censorship. Today{'}s social media landscape is littered with unfiltered content that can be anywhere from sli…
ClassificationGeneral Classificationtext-classificationText Classification+1