Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM

Agung Wiratmo; Chastine Fatichah

doi:10.22266/ijies2020.0430.27

Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM

Agung Wiratmo, Chastine Fatichah^*

^*Corresponding author for this work

Institut Teknologi Sepuluh Nopember

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

Distributed representation of a sentences cannot only be seen with the sequence but also with dependency. In this paper, we proposed an answer assessment model that considers with dependency relational each word. The dependency relational is obtained by universal dependency modelling from CoNLL format data. The dependency relational is used in Long Short-Term Memory (LSTM) architecture by modified the hidden state, which is called dependency tree LSTM. The proposed method has an improvement on QWK and accuracy in 2.38% and 2.05%, respectively, that compared with the LSTM state of the art in the English short essay. Furthermore, the proposed method with an Indonesian short essay shows the evaluation of QWK and accuracy of 68.07% and 82.51%, respectively.

Original language	English
Pages (from-to)	278-285
Number of pages	8
Journal	International Journal of Intelligent Engineering and Systems
Volume	13
Issue number	2
DOIs	https://doi.org/10.22266/ijies2020.0430.27
Publication status	Published - Jan 2020

Keywords

Dependency relational
Dependency tree LSTM
Short essay assessment
Transfer learning

Access to Document

10.22266/ijies2020.0430.27

Cite this

@article{80824ae715f244f4864cb6c224318d7b,

title = "Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM",

abstract = "Distributed representation of a sentences cannot only be seen with the sequence but also with dependency. In this paper, we proposed an answer assessment model that considers with dependency relational each word. The dependency relational is obtained by universal dependency modelling from CoNLL format data. The dependency relational is used in Long Short-Term Memory (LSTM) architecture by modified the hidden state, which is called dependency tree LSTM. The proposed method has an improvement on QWK and accuracy in 2.38% and 2.05%, respectively, that compared with the LSTM state of the art in the English short essay. Furthermore, the proposed method with an Indonesian short essay shows the evaluation of QWK and accuracy of 68.07% and 82.51%, respectively.",

keywords = "Dependency relational, Dependency tree LSTM, Short essay assessment, Transfer learning",

author = "Agung Wiratmo and Chastine Fatichah",

note = "Publisher Copyright: {\textcopyright} 2020",

year = "2020",

month = jan,

doi = "10.22266/ijies2020.0430.27",

language = "English",

volume = "13",

pages = "278--285",

journal = "International Journal of Intelligent Engineering and Systems",

issn = "2185-310X",

publisher = "Intelligent Networks and Systems Society",

number = "2",

}

TY - JOUR

T1 - Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM

AU - Wiratmo, Agung

AU - Fatichah, Chastine

PY - 2020/1

Y1 - 2020/1

N2 - Distributed representation of a sentences cannot only be seen with the sequence but also with dependency. In this paper, we proposed an answer assessment model that considers with dependency relational each word. The dependency relational is obtained by universal dependency modelling from CoNLL format data. The dependency relational is used in Long Short-Term Memory (LSTM) architecture by modified the hidden state, which is called dependency tree LSTM. The proposed method has an improvement on QWK and accuracy in 2.38% and 2.05%, respectively, that compared with the LSTM state of the art in the English short essay. Furthermore, the proposed method with an Indonesian short essay shows the evaluation of QWK and accuracy of 68.07% and 82.51%, respectively.

AB - Distributed representation of a sentences cannot only be seen with the sequence but also with dependency. In this paper, we proposed an answer assessment model that considers with dependency relational each word. The dependency relational is obtained by universal dependency modelling from CoNLL format data. The dependency relational is used in Long Short-Term Memory (LSTM) architecture by modified the hidden state, which is called dependency tree LSTM. The proposed method has an improvement on QWK and accuracy in 2.38% and 2.05%, respectively, that compared with the LSTM state of the art in the English short essay. Furthermore, the proposed method with an Indonesian short essay shows the evaluation of QWK and accuracy of 68.07% and 82.51%, respectively.

KW - Dependency relational

KW - Dependency tree LSTM

KW - Short essay assessment

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85099479720&partnerID=8YFLogxK

U2 - 10.22266/ijies2020.0430.27

DO - 10.22266/ijies2020.0430.27

M3 - Article

AN - SCOPUS:85099479720

SN - 2185-310X

VL - 13

SP - 278

EP - 285

JO - International Journal of Intelligent Engineering and Systems

JF - International Journal of Intelligent Engineering and Systems

IS - 2

ER -

Indonesian Short Essay Scoring Using Transfer Learning Dependency Tree LSTM

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this