Grammatical Error Correction with Neural Reinforcement Learning
نویسندگان
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.
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 کاملThe 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 کاملGrammatical 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 کاملDynamic 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 کاملNeural 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