Abstract

Several methods for automatic essay scoring (AES) for English language have been proposed. However, multi-aspect AES systems for other languages are unusual. Therefore, we propose a multi-aspect AES system to apply on a dataset of Brazilian Portuguese essays, which human experts evaluated according to five aspects defined by Brazilian Government to the National Exam to High School Student (ENEM). These aspects are skills that student must master and every skill is assessed apart from each other. Besides the prediction of each aspect, the feature analysis also was performed for each aspect. The AES system proposed employs several features already employed by AES systems for English language. Our results show that predictions for some aspects performed well with the features we employed, while predictions for other aspects performed poorly. Also, it is possible to note the difference between the five aspects in the detailed feature analysis we performed. Besides these contributions, the eight millions of enrollments every year for ENEM raise some challenge issues for future directions in our research.

Highlights

  • The goal of automatic essay scoring (AES) systems is to score a given essay

  • There are thousands of essays written to ENEM every year, to the best of our knowledge there is no AES system for Brazilian Portuguese (BP) language, or an analysis of features in a multi-aspect essay scoring system for BP

  • The main features used by e-rater are grouped into the following types: grammar, usage, mechanics, and style; organization and development; lexical complexity; and prompt-specific vocabulary usage. e-rater employs multiple regression, and it is task independent AES system, i.e., its score is independent of the given prompt

Read more

Summary

Introduction

AES systems are relevant for educational institutions, since the human effort to evaluate essays is high and, and students need feedback to improve his or her writing skills. Besides these issues, almost every senior high school student in Brazil should write an essay to the National Exam of High School (ENEM), which Brazilian government uses to evaluate the quality of high schooler’s education and that of their institution. Attali and Burstein (Attali and Burstein, 2006) proposed an AES system, called e-rater, that employs general features of argumentative essays to scoring prediction. The main features used by e-rater are grouped into the following types: grammar, usage, mechanics, and style; organization and development; lexical complexity; and prompt-specific vocabulary usage. e-rater employs multiple regression, and it is task independent AES system, i.e., its score is independent of the given prompt

Objectives
Methods
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call