Native Language Identification on Text and Speech

2017/07/22 by Marcos Zampieri, Zampieri, Marcos, Alina Maria Ciobanu +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.1707.07182

Proceedings of the Workshop on Innovative Use of NLP for Building Educational Applications (BEA)

arxiv created 2017/07/22 · arxiv updated 2017/07/25

Abstract

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 essays and spoken responses in form of audio transcriptions and iVectors by non-native English speakers of eleven native languages. Our system competed in the challenge under the team name ZCD and was based on an ensemble of SVM classifiers trained on character n-grams achieving 83.58% accuracy and ranking 3rd in the shared task.

Related

• Native Language Identification using i-vector
• Native Language Identification with Large Language Models
• Can string kernels pass the test of time in Native Language Identification?
• Discriminating between Indo-Aryan Languages Using SVM Ensembles
• SIGTYP 2021 Shared Task: Robust Spoken Language Identification