scholarly journals Machine Learning-Based Grammar Error Detection Method in English Composition

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jianbin Zhu ◽  
Xiaojun Shi ◽  
Shuanghua Zhang
Keyword(s):  
Machine Learning ◽  
Error Correction ◽  
Error Detection ◽  
Input Sequence ◽  
English Composition ◽  
Deep Model ◽  
Error Detection And Correction ◽  
Grammatical Errors ◽  
Grammatical Error ◽  
Transformer Model

The detection of grammatical errors in English composition is an important task in the field of NLP. The main purpose of this task is to check out grammatical errors in English sentences and correct them. Grammatical error detection and correction are important applications in the automatic proofreading of English texts and in the field of English learning aids. With the increasing influence of English on a global scale, a huge breakthrough has been made in the task of detecting English grammatical errors. Based on machine learning, this paper designs a new method for detecting grammatical errors in English composition. First, this paper implements a grammatical error detection model based on Seq2Seq. Second, this paper implements a grammatical error detection and correction scheme based on the Transformer model. The Transformer model performs better than most grammar models. Third, this paper realizes the application of the BERT model in grammar error detection and error correction tasks, and the generalization ability of the model has been significantly enhanced. This solves the problem that the forward and backward cannot be merged when the Transformer trains the language model. Fourth, this paper proposes a method of grammatical error detection and correction in English composition based on a hybrid model. According to specific application scenarios, the corresponding neural network model is used for grammatical error correction. Combine the Seq2Seq structure to encode the input sequence and automate feature engineering. Through the combination of traditional model and deep model, the advantages are complemented to realize grammatical error detection and automatic correction.

scholarly journals Lookup Table Algorithm for Error Correction in Color Images

2018 ◽  
Vol 2 (2) ◽  
pp. 63
Author(s):  
Ruaa Alaadeen Abdulsattar ◽  
Nada Hussein M. Ali
Keyword(s):  
Error Correction ◽  
Error Detection ◽  
Color Image ◽  
Color Images ◽  
Lookup Table ◽  
Hamming Code ◽  
Detection Techniques ◽  
Error Ratio ◽  
Error Detection And Correction ◽  
Large Burst

Error correction and error detection techniques are often used in wireless transmission systems. A color image of type BMP is considered as an application of developed lookup table algorithms to detect and correct errors in these images. Decimal Matrix Code (DMC) and Hamming code (HC) techniques were integrated to compose Hybrid Matrix Code (HMC) to maximize the error detection and correction. The results obtained from HMC still have some error not corrected because the redundant bits added by Hamming codes to the data are considered inadequate, and it is suitable when the error rate is low for detection and correction processes. Besides, a Hamming code could not detect large burst error period, in addition, the have same values sometimes which lead to not detect the error and consequently increase the error ratio. The proposed algorithm LUT_CORR is presented to detect and correct errors in color images over noisy channels, the proposed algorithm depends on the parallel Cyclic Redundancy Code (CRC) method that's based on two algorithms: Sarwate and slicing By N algorithms. The LUT-CORR and the aforementioned algorithms were merged to correct errors in color images, the output results correct the corrupted images with a 100 % ratio almost. The above high correction ratio due to some unique values that the LUT-CORR algorithm have. The HMC and the proposed algorithm applied to different BMP images, the obtained results from LUT-CORR are compared to HMC for both Mean Square Error (MSE) and correction ratio.  The outcome from the proposed algorithm shows a good performance and has a high correction ratio to retrieve the source BMP image.

Better Performance with Transformer: CPPFormer in precise prediction of cell-Penetrating Peptides

2021 ◽  
Vol 28 ◽  
Author(s):  
Yuyang Xue ◽  
Xiucai Ye ◽  
Lesong Wei ◽  
Xin Zhang ◽  
Tetsuya Sakurai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Cell Penetrating Peptides ◽  
Machine Learning Techniques ◽  
Superior Performance ◽  
Practical Applications ◽  
Deep Model ◽  
Cell Penetrating ◽  
Precise Prediction ◽  
Transformer Model

: With its superior performance, the Transformer model, which is based on the 'Encoder-Decoder' paradigm, has become the mainstream in natural language processing. On the other hand, bioinformatics has embraced machine learning and made great progress in drug design and protein property prediction. Cell-penetrating peptides (CPPs) are one kind of permeable protein that is convenient as a kind of 'postman' in drug penetration tasks. However, a small number of CPPs have been discovered by research, let alone practical applications in drug permeability. Therefore, correctly identifying the CPPs has opened up a new way to take macromolecules into cells without other potentially harmful materials in the drug. Most of the previous work only uses trivial machine learning techniques and hand-crafted features to construct a simple classifier. In CPPFormer, we learn from the idea of implementing the attention structure of Transformer, rebuilding the network based on the characteristics of CPPs according to its short length, and using an automatic feature extractor with a few manual engineered features to co-direct the predicted results. Compared to all previous methods and other classic text classification models, the empirical result has shown that our proposed deep model-based method has achieved the best performance of 92.16% accuracy in the CPP924 dataset and has passed various index tests.

scholarly journals Error Detection and Correction On-Board Nanosatellites Using Hamming Codes

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Caleb Hillier ◽  
Vipin Balyan
Keyword(s):  
Error Correction ◽  
Error Detection ◽  
Simulation Software ◽  
Hamming Code ◽  
Single Event ◽  
Hamming Codes ◽  
Single Event Effects ◽  
Effective Version ◽  
Fast Speed ◽  
Error Detection And Correction

The field of nanosatellites is constantly evolving and growing at a very fast speed. This creates a growing demand for more advanced and reliable EDAC systems that are capable of protecting all memory aspects of satellites. The Hamming code was identified as a suitable EDAC scheme for the prevention of single event effects on-board a nanosatellite in LEO. In this paper, three variations of Hamming codes are tested both in Matlab and VHDL. The most effective version was Hamming [16, 11, 4]2. This code guarantees single-error correction and double-error detection. All developed Hamming codes are suited for FPGA implementation, for which they are tested thoroughly using simulation software and optimized.

Design of High-Speed Decoder for New High-Speed Bus

2010 ◽  
Vol 20-23 ◽  
pp. 958-962
Author(s):  
Wei Gong Zhang ◽  
Bo Yang ◽  
Rui Ding ◽  
Yong Qin Hu
Keyword(s):  
Error Correction ◽  
Intelligent Control ◽  
Error Detection ◽  
High Speed ◽  
Critical Path ◽  
Speed Error ◽  
Error Detection And Correction ◽  
Traditional Algorithm ◽  
New Type ◽  
Correction System

This paper presents a new type of high-speed error correction for the requirements of new high-Speed Bus. Use RS (255, 239). Not only optimization traditional algorithm, but also design bidirectional synchronous calculated adjoint form module, Fast B-M algorithm module. and full parallel Chien Search module. These design used in new high-Speed Bus, Larger than usual decoder designed to significantly shorten the critical path decoding, and achieve continuous decoding. In addition, this error correction system separated error detection and correction module modules, And after error detection module add intelligent control, which reduced the complexity and power consumption of equipment. The error correction system design for the requirements of the new bus which speed is above 400m / s.

What does a Man do after he Makes an Error? An Analysis of Response Programming

1977 ◽  
Vol 29 (4) ◽  
pp. 727-743 ◽  
Author(s):  
Patrick Rabbitt ◽  
Bryan Rodgers
Keyword(s):  
Information Processing ◽  
Error Correction ◽  
Error Detection ◽  
Single Channel ◽  
Previous Trial ◽  
Limited Capacity ◽  
Error Detection And Correction ◽  
Channel Information ◽  
The Subject ◽  
Response Programming

When people make errors during continuous tasks they temporarily pause and then slow down. One line of explanation has been that they monitor feedback to detect errors, that they may make incidental responses when errors occur (e.g. they may swear) and that they may pause to analyse their errors. In all these cases they may be assumed to act as single channel information processing systems of limited capacity, and to be unable to recognise any new signal until these processes have been completed. Analysis of response after errors shows that this cannot be the case. Responses after errors are inaccurate, but are not slow when they require the subject to make the response which he should have made on the previous trial (i.e. to make an error correction response). Subjects thus must recognise new signals as soon as they occur. The present results require a new model of error detection and correction, and a model for response programming and priming.

scholarly journals Korean Grammatical Error Correction Based on Transformer with Copying Mechanisms and Grammatical Noise Implantation Methods

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2658
Author(s):  
Myunghoon Lee ◽  
Hyeonho Shin ◽  
Dabin Lee ◽  
Sung-Pil Choi
Keyword(s):  
Neural Networks ◽  
Error Correction ◽  
Deep Neural Networks ◽  
Language Models ◽  
Grammatical Errors ◽  
Grammatical Error

Grammatical Error Correction (GEC) is the task of detecting and correcting various grammatical errors in texts. Many previous approaches to the GEC have used various mechanisms including rules, statistics, and their combinations. Recently, the performance of the GEC in English has been drastically enhanced due to the vigorous applications of deep neural networks and pretrained language models. Following the promising results of the English GEC tasks, we apply the Transformer with Copying Mechanism into the Korean GEC task by introducing novel and effective noising methods for constructing Korean GEC datasets. Our comparative experiments showed that the proposed system outperforms two commercial grammar check and other NMT-based models.

Taking DDL online

2020 ◽  
Vol 43 (2) ◽  
pp. 169-195 ◽  
Author(s):  
Peter Crosthwaite
Keyword(s):  
Error Correction ◽  
Academic Writing ◽  
Error Detection ◽  
Data Driven ◽  
Online Course ◽  
Design And Implementation ◽  
Methodological Challenges ◽  
Error Detection And Correction

Abstract This paper describes the rationale, design and implementation of a short private online course (SPOC) on data-driven learning (DDL) (Johns, 1991), focusing on L2 error correction in postgraduate academic writing and involving over 300 registered users. I discuss the affordances of using a SPOC platform (namely EdX) for online DDL training, describing activities that cover a range of useful strategies for DDL-led error detection and correction. Learners’ usage of the SPOC platform and their quantitative and qualitative perceptions of the course are described for the reader. The paper also outlines certain conceptual and methodological challenges involved in taking DDL instruction online.

Design and Implementation of CRC Error Correction for ADS-B System Responding Based on FPGA

2014 ◽  
Vol 577 ◽  
pp. 994-997 ◽  
Author(s):  
Yu Ping Ma ◽  
Jun Zhang
Keyword(s):  
Error Correction ◽  
Error Detection ◽  
Signal Transmission ◽  
Confidence Judgment ◽  
Verilog Hdl ◽  
Correction Process ◽  
Signal Error ◽  
Error Detection And Correction ◽  
Working Principle ◽  
Error Correction Algorithm

Automatic Dependent Surveillance Broadcast (ADS-B) system signal error detection and correction process scheme are introduced in this paper, and the working principle of cyclic redundancy check (CRC) is described. Then, this paper provides an error correction algorithm based on the confidence judgment and an error correction process flow chart based on ADS-B system. Finally, the design of CRC checksum is performed by taking use of Verilog HDL, and the simulation and verification are achieved in Modelism software platform. Experimental results show that the algorithm can carry out verification and error correction for ADS-B responding signal and can improve the reliability of ADS-B system signal transmission.

Sign in / Sign up

Export Citation Format

Share Document