Automatically grading learners' English using a Gaussian process

نویسندگان

  • Rogier C. van Dalen
  • Kate Knill
  • Mark J. F. Gales
چکیده

There is a high demand around the world for the learning of English as a second language. Correspondingly, there is a need to assess the proficiency level of learners both during their studies and for formal qualifications. A number of automatic methods have been proposed to help meet this demand with varying degrees of success. This paper considers the automatic assessment of spoken English proficiency, which is still a challenging problem. In this scenario, the grader should be able to accurately assess the learner’s ability level from spontaneous, prompted, speech, independent of L1 language and the quality of the audio recording. Automatic graders are potentially more consistent than humans. However, the validity of the predicted grade varies. This paper proposes an automatic grader based on a Gaussian process. The advantage of using a Gaussian process is that as well as predicting a grade, it provides a measure of the uncertainty of its prediction. The uncertainty measure is sufficiently accurate to decide which automatic grades should be re-graded by humans. It can also be used to determine which candidates are hard to grade for humans and therefore need expert grading. Performance of the automatic grader is shown to be close to human graders on real candidate entries. Interpolation of human and GP grades further boosts performance.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Grading, no longer an obstacle to learners’ attendance to teacher feedback

Learners are often reported not to be motivated enough to attend to teacher feedback. Teachers also  tend  to  grade  learners’  writing  samples  when  providing  them  with  corrective  feedback though  they  know  it  may  divert  their  attention  away  from  teacher  feedback.  However,  not grading learner writings does not seem to be an option due to both learners’ demands for it and ins...

متن کامل

The Human Kernel

Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kernels struggle on function extrapolation problems that are trivial for human lea...

متن کامل

The Use of Technology in English Language Learning: A Literature Review

The use of technology has become an important part of the learning process in and out of the class. Every language class usually uses some form of technology. Technology has been used to both help and improve language learning. Technology enables teachers to adapt classroom activities, thus enhancing the language learning process. Technology continues to grow in importance as a tool to help tea...

متن کامل

The Effects of Types of Writing Approaches on Iranian EFL Learners’ Writing Performance and Their Attitudes toward Writing Skill

The main purpose of the present quasi-experimental study was twofold; its first purpose was to investigate the effects of using of two approaches namely; genre and process on EFL learners’ accuracy, fluency, and complexity in written task production. Secondly, it attempted to investigate the effects of mentioned approaches on EFL learners’ attitude toward writing skill. to this end, 60 learners...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015