Ontology of academic sentence dependencies for a verb choice suggestion

Sarunya Kanjanawattana, Masaomi Kimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Non-native researchers encountered a problem of lacking academic writing skill. During the writing, we may accidentally use a word repeatedly due to our familiarity that reduces a quality of writing. To solve the problem, a paraphrase is a good option. It helps the manuscript read more flowery by reducing duplicate words and refining sentence alignments. In this study, we propose a novel idea to use a sentence dependency ontology to suggest possible verbs replaceable on existing context without influence to the original intention. We created an ontology-based system and designed a new ontology. To discover a list of verb choices, our idea is based on sentence dependency, especially a dependency between subject and verb (nsubj) as well as a relationship between verb and object (dobj). We chose them because these two dependencies had a strong relationship to the verb of the sentence. To evaluate the system, we compared the efficiencies of two different systems, i.e., a tradition system utilizing synonyms as word choices and our ontology-based system. As the results, ours provided the better performance rather than the traditional system. This clarifies that our system should be a proper solution for studies on paraphrasing.

Original languageEnglish
Title of host publication2018 13th International Conference on Digital Information Management, ICDIM 2018
EditorsEzendu Ariwa, Pit Pichappan, Pit Pichappan, Wael M El-Medany, Asif Naeem
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages39-44
Number of pages6
ISBN (Electronic)9781538652435
DOIs
Publication statusPublished - 2018 Sep
Event13th International Conference on Digital Information Management, ICDIM 2018 - Berlin, Germany
Duration: 2018 Sep 242018 Sep 26

Publication series

Name2018 13th International Conference on Digital Information Management, ICDIM 2018

Conference

Conference13th International Conference on Digital Information Management, ICDIM 2018
CountryGermany
CityBerlin
Period18/9/2418/9/26

Fingerprint

ontology
Ontology
Refining
Computer systems
efficiency
performance

Keywords

  • Natural language processing
  • Ontology
  • Paraphrase
  • Sentence dependency
  • Word choices suggestion

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems and Management
  • Media Technology
  • Communication

Cite this

Kanjanawattana, S., & Kimura, M. (2018). Ontology of academic sentence dependencies for a verb choice suggestion. In E. Ariwa, P. Pichappan, P. Pichappan, W. M. El-Medany, & A. Naeem (Eds.), 2018 13th International Conference on Digital Information Management, ICDIM 2018 (pp. 39-44). [8847019] (2018 13th International Conference on Digital Information Management, ICDIM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDIM.2018.8847019

Ontology of academic sentence dependencies for a verb choice suggestion. / Kanjanawattana, Sarunya; Kimura, Masaomi.

2018 13th International Conference on Digital Information Management, ICDIM 2018. ed. / Ezendu Ariwa; Pit Pichappan; Pit Pichappan; Wael M El-Medany; Asif Naeem. Institute of Electrical and Electronics Engineers Inc., 2018. p. 39-44 8847019 (2018 13th International Conference on Digital Information Management, ICDIM 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kanjanawattana, S & Kimura, M 2018, Ontology of academic sentence dependencies for a verb choice suggestion. in E Ariwa, P Pichappan, P Pichappan, WM El-Medany & A Naeem (eds), 2018 13th International Conference on Digital Information Management, ICDIM 2018., 8847019, 2018 13th International Conference on Digital Information Management, ICDIM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 39-44, 13th International Conference on Digital Information Management, ICDIM 2018, Berlin, Germany, 18/9/24. https://doi.org/10.1109/ICDIM.2018.8847019
Kanjanawattana S, Kimura M. Ontology of academic sentence dependencies for a verb choice suggestion. In Ariwa E, Pichappan P, Pichappan P, El-Medany WM, Naeem A, editors, 2018 13th International Conference on Digital Information Management, ICDIM 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 39-44. 8847019. (2018 13th International Conference on Digital Information Management, ICDIM 2018). https://doi.org/10.1109/ICDIM.2018.8847019
Kanjanawattana, Sarunya ; Kimura, Masaomi. / Ontology of academic sentence dependencies for a verb choice suggestion. 2018 13th International Conference on Digital Information Management, ICDIM 2018. editor / Ezendu Ariwa ; Pit Pichappan ; Pit Pichappan ; Wael M El-Medany ; Asif Naeem. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 39-44 (2018 13th International Conference on Digital Information Management, ICDIM 2018).
@inproceedings{bee1e75f5df2477eb592c8f0fcb86e8c,
title = "Ontology of academic sentence dependencies for a verb choice suggestion",
abstract = "Non-native researchers encountered a problem of lacking academic writing skill. During the writing, we may accidentally use a word repeatedly due to our familiarity that reduces a quality of writing. To solve the problem, a paraphrase is a good option. It helps the manuscript read more flowery by reducing duplicate words and refining sentence alignments. In this study, we propose a novel idea to use a sentence dependency ontology to suggest possible verbs replaceable on existing context without influence to the original intention. We created an ontology-based system and designed a new ontology. To discover a list of verb choices, our idea is based on sentence dependency, especially a dependency between subject and verb (nsubj) as well as a relationship between verb and object (dobj). We chose them because these two dependencies had a strong relationship to the verb of the sentence. To evaluate the system, we compared the efficiencies of two different systems, i.e., a tradition system utilizing synonyms as word choices and our ontology-based system. As the results, ours provided the better performance rather than the traditional system. This clarifies that our system should be a proper solution for studies on paraphrasing.",
keywords = "Natural language processing, Ontology, Paraphrase, Sentence dependency, Word choices suggestion",
author = "Sarunya Kanjanawattana and Masaomi Kimura",
year = "2018",
month = "9",
doi = "10.1109/ICDIM.2018.8847019",
language = "English",
series = "2018 13th International Conference on Digital Information Management, ICDIM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "39--44",
editor = "Ezendu Ariwa and Pit Pichappan and Pit Pichappan and El-Medany, {Wael M} and Asif Naeem",
booktitle = "2018 13th International Conference on Digital Information Management, ICDIM 2018",

}

TY - GEN

T1 - Ontology of academic sentence dependencies for a verb choice suggestion

AU - Kanjanawattana, Sarunya

AU - Kimura, Masaomi

PY - 2018/9

Y1 - 2018/9

N2 - Non-native researchers encountered a problem of lacking academic writing skill. During the writing, we may accidentally use a word repeatedly due to our familiarity that reduces a quality of writing. To solve the problem, a paraphrase is a good option. It helps the manuscript read more flowery by reducing duplicate words and refining sentence alignments. In this study, we propose a novel idea to use a sentence dependency ontology to suggest possible verbs replaceable on existing context without influence to the original intention. We created an ontology-based system and designed a new ontology. To discover a list of verb choices, our idea is based on sentence dependency, especially a dependency between subject and verb (nsubj) as well as a relationship between verb and object (dobj). We chose them because these two dependencies had a strong relationship to the verb of the sentence. To evaluate the system, we compared the efficiencies of two different systems, i.e., a tradition system utilizing synonyms as word choices and our ontology-based system. As the results, ours provided the better performance rather than the traditional system. This clarifies that our system should be a proper solution for studies on paraphrasing.

AB - Non-native researchers encountered a problem of lacking academic writing skill. During the writing, we may accidentally use a word repeatedly due to our familiarity that reduces a quality of writing. To solve the problem, a paraphrase is a good option. It helps the manuscript read more flowery by reducing duplicate words and refining sentence alignments. In this study, we propose a novel idea to use a sentence dependency ontology to suggest possible verbs replaceable on existing context without influence to the original intention. We created an ontology-based system and designed a new ontology. To discover a list of verb choices, our idea is based on sentence dependency, especially a dependency between subject and verb (nsubj) as well as a relationship between verb and object (dobj). We chose them because these two dependencies had a strong relationship to the verb of the sentence. To evaluate the system, we compared the efficiencies of two different systems, i.e., a tradition system utilizing synonyms as word choices and our ontology-based system. As the results, ours provided the better performance rather than the traditional system. This clarifies that our system should be a proper solution for studies on paraphrasing.

KW - Natural language processing

KW - Ontology

KW - Paraphrase

KW - Sentence dependency

KW - Word choices suggestion

UR - http://www.scopus.com/inward/record.url?scp=85073497724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073497724&partnerID=8YFLogxK

U2 - 10.1109/ICDIM.2018.8847019

DO - 10.1109/ICDIM.2018.8847019

M3 - Conference contribution

AN - SCOPUS:85073497724

T3 - 2018 13th International Conference on Digital Information Management, ICDIM 2018

SP - 39

EP - 44

BT - 2018 13th International Conference on Digital Information Management, ICDIM 2018

A2 - Ariwa, Ezendu

A2 - Pichappan, Pit

A2 - Pichappan, Pit

A2 - El-Medany, Wael M

A2 - Naeem, Asif

PB - Institute of Electrical and Electronics Engineers Inc.

ER -