Text Analyzer for Competitive Examination

Full Text (PDF, 326KB), PP.25-34

Views: 0 Downloads: 0


Ashwini Dalvi 1 Irfan Siddavatam 1 Sagar Ailani 1 Smith Dedhia 1 Shyamal Makwana 1

1. Department of Information Technology, K.J.Somaiya College of Engineering, Mumbai-400077,India

* Corresponding author.

DOI: https://doi.org/10.5815/ijeme.2019.06.03

Received: 6 Jul. 2019 / Revised: 2 Aug. 2019 / Accepted: 30 Aug. 2019 / Published: 8 Nov. 2019

Index Terms

GRE, TOEFL, NLP, text processing, topic modeling


Competitive examination provide a platform to the user for gauging their verbal and literature skills. The tools available currently only provide some simple feature regarding text processing such as spelling correction and providing different synonyms of the selected words. A complete assessment is not done for the user’s abilities and relevant details related to the context are not taken entirely into consideration. The following paper proposes a way to implement Natural Language Processing on text to provide feedback to the user for their competitive examinations. The assessment of the text will be done according to the parameter such as grammar, vocabulary; relevance to the context.
Some applications for web and mobile platform are available to offer assessment of English language essay but limited academic research available to validate research work in this domain. This work is effort to address requirement of text analyzer for English language evaluation methods incorporating natural language processing.

Cite This Paper

Ashwini Dalvi, Irfan Siddavatam, Sagar Ailani, Smith Dedhia, Shyamal Makwana," Text Analyzer for Competitive Examination", International Journal of Education and Management Engineering(IJEME), Vol.9, No.5, pp.25-34, 2019. DOI: 10.5815/ijeme.2019.06.03


[1]Rada Mihalcea, Courtney Corley, Carlo Strapparava, "Corpus-based and Knowledge-based Measures of Text Semantic Similarity", 2006.

[2]E Gabrilovich, S Markovitch, “Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis” (2007). IJcAI 7, 1606-1611

[3]Moore, Brian J. "A Real-Time N-Gram Approach to Choosing Synonyms Based on Context."

[4]Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jefferey Dean "Distributed Representations of Words and Phrases and their Compositionality," 2013

[5]Casey Whitelaw, Ben Hutchinson, Grace Y. Chung Gerard Ellis "Using the Web for Language Independent Spellchecking and Autocorrection," 2009 Google Inc.

[6]Monojit Choudhury, Markose Thomas, Animesh Mukherjee, Anupam Basu, Niloy Ganguly "How Difficult is it to Develop a Perfect Spell-checker? A Cross-linguistic Analysis through Complex Network Approach," 2007 Association for Computational Linguistics

[7]Chen, Danqi, Manning, Christoper "A Fast and Accurate Dependency Parser using Neural Networks," 2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

[8]Brian J. Moore, Robert Mercer "A Real-Time N-Gram Approach to Choosing Synonyms Based on Context," 2015 Electronic Thesis and Dissertation Repository

[9]Wikipedia Dumps, https://meta.wikimedia.org/wiki/Data_dumps

[10]Reading Wikipedia XML Dumps with Python, https://www.heatonresearch.com/2017/03/03/ python-basic-wikipedia -parsing.html

[11]Marian Neural Machine Translation, https://marian-nmt.github.io

[12]Oren Melamud, Omer Levy, Ido Dagan, “A Simple Word Embedding Model for Lexical Substitution”. Proceedings of NAACL-HLT 2015

[13]Free Online GRE AWA Essay Grader - MBA Crystal Ball https://www.mbacrystalball.com/gre/gre- essay- grader

[14]AWA Professor: Expert GMAT & GRE AWA Essay Raters https://www.awaprofessor.com

[15]testbig.com | TOEFL IELTS GMAT GRE SAT ACT PTE ESL. https://www.testbig.com/

[16]ETS Criterion writing evaluation service http://www.ets.org/criterion