Arabic Short Answer Scoring with Effective Feedback for Students
Wael Hassan Gomaa,Aly A. Fahmy +1 more
TLDR
Overall, the obtained correlation and error rate results prove that the presented system performs well enough for deployment in a real scoring environment.Abstract:
In this paper, we explore text similarity techniques for the task of automatic short answer scoring in Arabic language. We compare a number of string-based and corpus-based similarity measures, evaluate the effect of combining these measures, handle student’s answers holistically and partially, provide immediate useful feedback to student and also introduce a new benchmark Arabic data set that contains 50 questions and 600 student answers. Overall, the obtained correlation and error rate results prove that the presented system performs well enough for deployment in a real scoring environment. General Terms Natural Language Processing, Text Miningread more
Citations
More filters
Journal ArticleDOI
A Review and Future Perspectives of Arabic Question Answering Systems
Santosh Kumar Ray,Khaled Shaalan +1 more
TL;DR: The most commonly used architecture for the development of an Arabic QAS, known as pipeline architecture, has been presented and a list of techniques, tools, and computational linguistic resources, required to implement the components of the presented pipelined architecture, are described.
Book ChapterDOI
Ans2vec: A Scoring System for Short Answers
Wael Hassan Gomaa,Aly A. Fahmy +1 more
TL;DR: An efficient and uncomplicated short answer grading model named Ans2vec is proposed, used to convert both model and student’s answers into meaningful vectors to measure the similarity between them.
Journal ArticleDOI
A multi-approach to community question answering
Yassine El Adlouni,Horacio Rodríguez,Mohammed Meknassi,Said Ouatik El Alaoui,Noureddine En-Nahnahi +4 more
TL;DR: A bunch of unsupervised models are proposed and it is shown that a model based on Latent Semantic Indexing approach outperforms state of the art models for this task and transfer learning is used to power the embeddings layer of various deep learning models.
Proceedings ArticleDOI
An automated scoring approach for Arabic short answers essay questions
Hebah Rababah,Ahmad T. Al-Taani +1 more
TL;DR: An automated scoring approach for short answers to Arabic essay questions is proposed based on the similarity between the student's answer and model answer, cosine similarity measure is used for this purpose.
Journal ArticleDOI
AraScore: A deep learning-based system for Arabic short answer scoring
TL;DR: In this article , the first deep learning-based system for Arabic short answer scoring is introduced, which can help teachers in the Arab world better utilize their time in other teaching activities that would elevate the quality of learning in the region.
References
More filters
Journal ArticleDOI
The WEKA data mining software: an update
TL;DR: This paper provides an introduction to the WEKA workbench, reviews the history of the project, and, in light of the recent 3.6 stable release, briefly discusses what has been added since the last stable version (Weka 3.4) released in 2003.
Journal ArticleDOI
A Survey of Text Similarity Approaches
Wael Hassan Gomaa,Aly A. Fahmy +1 more
TL;DR: This survey discusses the existing works on text similarity through partitioning them into three approaches; String-based, Corpus-based and Knowledge-based similarities, and samples of combination between these similarities are presented.
Journal ArticleDOI
C-rater: Automated Scoring of Short-Answer Questions
Claudia Leacock,Martin Chodorow +1 more
TL;DR: C-rater is an automated scoring engine that has been developed to score responses to content-based short answer questions using predicateargument structure, pronominal reference, morphological analysis and synonyms to assign full or partial credit to a short answer question.
Journal ArticleDOI
Ckmeans.1d.dp: Optimal k-means Clustering in One Dimension by Dynamic Programming
Haizhou Wang,Mingzhou Song +1 more
TL;DR: In this paper, a dynamic programming algorithm for optimal one-dimensional clustering is proposed, which is implemented as an R package called Ckmeans.1d.dp.
Proceedings ArticleDOI
Text-to-Text Semantic Similarity for Automatic Short Answer Grading
Michael Mohler,Rada Mihalcea +1 more
TL;DR: This paper compares a number of knowledge-based and corpus-based measures of text similarity, evaluates the effect of domain and size on the corpus- based measures, and introduces a novel technique to improve the performance of the system by integrating automatic feedback from the student answers.