Grammatical Error Correction with Neural Reinforcement Learning

نویسندگان

  • Keisuke Sakaguchi
  • Matt Post
  • Benjamin Van Durme
چکیده

We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a sentence-level, task-specific evaluation metric, avoiding the exposure bias issue in MLE. We demonstrate that NRL outperforms MLE both in human and automated evaluation metrics, achieving the state-ofthe-art on a fluency-oriented GEC corpus.

برای دانلود 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

The Impact of Immediate Grammatical Error Correction on Senior English Majors’ Accuracy at Hebron University

This study aimed at investigating the effects of grammatical error correction on EFL learners’ accuracy. Twenty-two male and female senior students were chosen randomly to respond to a questionnaire investigating their beliefs about immediate grammatical error correction.  Actually, the study was conducted in order to answer this question: what is the effect of grammatical error feedback on stu...

متن کامل

The Impact of Immediate Grammatical Error Correction on Senior English Majors’ Accuracy at Hebron University

This study aimed at investigating the effects of grammatical error correction on EFL learners’ accuracy. Twenty-two male and female senior students were chosen randomly to respond to a questionnaire investigating their beliefs about immediate grammatical error correction.  Actually, the study was conducted in order to answer this question: what is the effect of grammatical error feedback on stu...

متن کامل

Grammatical Error Correction of English as Foreign Language Learners

This study aimed to discover the insight of error correction by implementing two correction systems on three Iranian university students. The three students were invited to write four in-class essays throughout the semester, in which their verb errors and individual-selected errors were corrected using the Code Correction System and the Individual Correction System. At the end of the study, the...

متن کامل

Dynamic adaptation of quantization thresholds for soft-decision viterbi decoding with a reinforcement learning neural network

Two reinforcement learning neural network architectures which enhance the performance of a soft-decision Viterbi decoder used for forward error-correction in a digital communication system have been investigated and compared. Each reinforcement learning neural network is designed to work as a co-processor to a demodulator dynamically adapting the soft quantization thresholds toward optimal sett...

متن کامل

Neural Multi-task Learning in Automated Assessment

Grammatical error detection and automated essay scoring are two tasks in the area of automated assessment. Traditionally these tasks have been treated independently with different machine learning models and features used for each task. In this paper, we develop a multi-task neural network model that jointly optimises for both tasks, and in particular we show that neural automated essay scoring...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017