SCESS: a WFSA-based automated simplified chinese essay scoring system with incremental latent semantic analysis

Hao, Shudong; Xu, Yanyan; Deng, Ke; Su, Kaile; Peng, Hengli

doi:10.1017/s1351324914000138

Cited by 9 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future, the TASAG can be opened to other institutes for educational purposes by using web services. Moreover, other NLP methods such as the ontological approach [36], or multidimensional assessment method (Hoang and Ngamnij [37], or LSA derivatives [38], or Wikipedia-based explicit semantic analysis (ESA) [39,40], or ESA derivatives [41] can be used in future research. In this research, ESA was not utilized because ESA uses in a highdimensional space of natural concepts derived from Wikipedia, or, for Turkish, Vikipedi [42].…”

Section: Discussionmentioning

confidence: 99%

Web-Based Turkish Automatic Short-Answer Grading System

İnce¹,

Kutlu²

2021

NLPRE

View full text Add to dashboard Cite

In this paper, a web-based Turkish automatic short answer grading system (TASAG) is developed to score exam questions and to generate online exams for automatic scoring of short-answer questions. The novelty of this study is that TASAG is the first software of its kind for the Turkish language. The algorithm of the TASAG software is a hybrid that determines which method will be used at runtime based on the word number dimensions to achieve accurate scoring. To measure the software's accuracy, a case study is performed for computer engineering. Instructors' scoring results and the TASAG software scoring results were compared. Two instructors prepared different answer keys for the same exam to increase the accuracy of the scoring. The scoring results, which are compared in the figures, are very close to each other, which indicate the effectiveness of the TASAG software. Moreover, the TASAG arithmetic mean scores for each answer key are calculated and given as the final score for the exam. According to the results, the TASAG software can be used for automated short answer grading system in Turkish with a 92% success rate.

show abstract

Section: Discussionmentioning

confidence: 99%

Web-Based Turkish Automatic Short-Answer Grading System

İnce¹,

Kutlu²

2021

NLPRE

View full text Add to dashboard Cite

show abstract

“…They also developed detection rules based on the corpus to identify "biezi" in the text. Hao, S. et al [44] established a table of easily confused characters and used WFSA to detect "biezi" in compositions using an n-gram model while creating a table of commonly misspelled characters for correction. Wei, S. et al [45] labeled the positions of "biezi" and provided correction suggestions by combining the Soft-Masked BERT (Bidirectional Encoder Representations from Transformers) [46] model with tables of phonetically and visually similar characters.…”

Section: Spelling Errorsmentioning

confidence: 99%

Automatic Essay Evaluation Technologies in Chinese Writing—A Systematic Literature Review

Yang,

He,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Automatic essay evaluation, an essential application of natural language processing (NLP) technology in education, has been increasingly employed in writing instruction and language proficiency assessment. Because automatic Chinese Essay Evaluation (ACEE) has made some breakthroughs due to the rapid development of upstream Chinese NLP technology, many evaluation tools have been applied in teaching practice and high-risk evaluation processes. However, the development of ACEE is still in its early stages, with many technical bottlenecks and challenges. This paper systematically explores the current research status of corpus construction, feature engineering, and scoring models in ACEE through literature to provide a technical perspective for stakeholders in the ACEE research field. Literature research has shown that constructing the ACEE public corpus is insufficient and lacks an effective platform to promote the development of ACEE research. Various shallow and deep features can be extracted using statistical and NLP techniques in ACEE. However, there are still substantial limitations in extracting grammatical errors and features related to syntax and traditional Chinese Literary style. For the construction of scoring models, existing studies have shown that traditional machine learning and deep learning methods each have advantages in different corpora and feature selections. The deep learning model, which exhibits strong adaptability and multi-task joint learning potential, has broader development space regarding model scalability.

show abstract

“…In 2010, Peng attempted to adopt several vector space models and added some statistical surface features for Chinese text [25]. In 2016, Hao proposed the SCESS system based on Weighted Finite State Automata (WFSA) and used Incremental Latent Semantic Analysis (ILSA) to deal with a large number of essays [26]. The SCESS system constructed a WFSA to perform text pre-processing based on an N-gram language model and used ILSA to perform automated essay scoring.…”

Section: Related Workmentioning

confidence: 99%

An Automated Grader for Chinese Essay Combining Shallow and Deep Semantic Attributes

2019

View full text Add to dashboard Cite

Writing is a pivotal part of the language exam, which is considered as a useful tool to accurately reflect students' language competence. As Chinese language tests become popular, manual grading becomes a heavy and expensive task for language test organizers. In the past years, there is a large volume of research about the automated English evaluation systems. Nevertheless, since the Chinese text has more complex grammar and structure, much fewer studies have been investigated on automated Chinese evaluation systems. In this paper, we propose an automated Chinese essay evaluation system called AGCE (Automated Grader for Chinese Essay), which combines shallow and deep semantic attributes of essays. We implement and train our AGCE system on a Chinese essay dataset, which is created by ourselves based on more than 1000 student essays from a Chinese primary school. Experimental results indicate that our AGCE system achieves the quadratic weighted Kappa of 0.7590 on a small dataset, which is of higher grading accuracy compared with other four popular neural network methods trained on large-scale datasets. In addition, our AGCE system can provide constructive feedback about Chinese writing, such as misspelling feedback and grammatical feedback about writers' essays, which is helpful to improve their writing capability. INDEX TERMS Automated Chinese essay evaluation, AGCE, natural language processing, semantic attributes, semantic feedback.

show abstract

SCESS: a WFSA-based automated simplified chinese essay scoring system with incremental latent semantic analysis

Cited by 9 publications

References 34 publications

Web-Based Turkish Automatic Short-Answer Grading System

Web-Based Turkish Automatic Short-Answer Grading System

Automatic Essay Evaluation Technologies in Chinese Writing—A Systematic Literature Review

An Automated Grader for Chinese Essay Combining Shallow and Deep Semantic Attributes

Contact Info

Product

Resources

About