A Comparative Study of Different Models in Ancient Poetry Translation

Wang Boyuan; Le Xiangli; Wang Hainan; Zhang Baochang

doi:10.1109/ICIEA51954.2021.9516256

A Comparative Study of Different Models in Ancient Poetry Translation

Wang Boyuan
, Le Xiangli
, Wang Hainan
, Zhang Baochang^*

^*Corresponding author for this work

School of Artificial Intelligence(Institute of Artificial Intelligence)

Beihang University
Guiyang University
Shenzhen Academy of Aerospace Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Ancient poetry is an important part of Chinese culture. There have been projects like Jiuge to combine ancient poetry with deep learning. The language of ancient poetry is often refined, and it needs rich imagination to understand its meaning. As a result, it is difficult to automatically implement the translation. This paper makes a preliminary attempt in this aspect, based on the data set collected by ourselves, adopts deep encoder-decoder model, such as GRU, LSTM and Transformer models, to train our model. We compare the results of the three models, which have their own advantages and disadvantages. However, due to the size of the data set and the model itself, the effect is not very ideal, and still needs to be improved.

Original language	English
Title of host publication	Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2032-2036
Number of pages	5
ISBN (Electronic)	9781665422482
DOIs	https://doi.org/10.1109/ICIEA51954.2021.9516256
State	Published - 1 Aug 2021
Event	16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021 - Chengdu, China Duration: 1 Aug 2021 → 4 Aug 2021

Publication series

Name	Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021

Conference

Conference	16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021
Country/Territory	China
City	Chengdu
Period	1/08/21 → 4/08/21

Keywords

Transformer
ancient poetry
deep learning
machine translation
natural language processing
neural network
seq2seq model

Access to Document

10.1109/ICIEA51954.2021.9516256

Cite this

Boyuan, W., Xiangli, L., Hainan, W., & Baochang, Z. (2021). A Comparative Study of Different Models in Ancient Poetry Translation. In Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021 (pp. 2032-2036). (Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEA51954.2021.9516256

Boyuan, Wang ; Xiangli, Le ; Hainan, Wang et al. / A Comparative Study of Different Models in Ancient Poetry Translation. Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 2032-2036 (Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021).

@inproceedings{c9b36d8d18c7449693a2bc041f1dfda3,

title = "A Comparative Study of Different Models in Ancient Poetry Translation",

abstract = "Ancient poetry is an important part of Chinese culture. There have been projects like Jiuge to combine ancient poetry with deep learning. The language of ancient poetry is often refined, and it needs rich imagination to understand its meaning. As a result, it is difficult to automatically implement the translation. This paper makes a preliminary attempt in this aspect, based on the data set collected by ourselves, adopts deep encoder-decoder model, such as GRU, LSTM and Transformer models, to train our model. We compare the results of the three models, which have their own advantages and disadvantages. However, due to the size of the data set and the model itself, the effect is not very ideal, and still needs to be improved.",

keywords = "Transformer, ancient poetry, deep learning, machine translation, natural language processing, neural network, seq2seq model",

author = "Wang Boyuan and Le Xiangli and Wang Hainan and Zhang Baochang",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021 ; Conference date: 01-08-2021 Through 04-08-2021",

year = "2021",

month = aug,

day = "1",

doi = "10.1109/ICIEA51954.2021.9516256",

language = "英语",

series = "Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2032--2036",

booktitle = "Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021",

address = "美国",

}

Boyuan, W, Xiangli, L, Hainan, W & Baochang, Z 2021, A Comparative Study of Different Models in Ancient Poetry Translation. in Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021. Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021, Institute of Electrical and Electronics Engineers Inc., pp. 2032-2036, 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021, Chengdu, China, 1/08/21. https://doi.org/10.1109/ICIEA51954.2021.9516256

A Comparative Study of Different Models in Ancient Poetry Translation. / Boyuan, Wang; Xiangli, Le; Hainan, Wang et al.
Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2032-2036 (Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Comparative Study of Different Models in Ancient Poetry Translation

AU - Boyuan, Wang

AU - Xiangli, Le

AU - Hainan, Wang

AU - Baochang, Zhang

PY - 2021/8/1

Y1 - 2021/8/1

N2 - Ancient poetry is an important part of Chinese culture. There have been projects like Jiuge to combine ancient poetry with deep learning. The language of ancient poetry is often refined, and it needs rich imagination to understand its meaning. As a result, it is difficult to automatically implement the translation. This paper makes a preliminary attempt in this aspect, based on the data set collected by ourselves, adopts deep encoder-decoder model, such as GRU, LSTM and Transformer models, to train our model. We compare the results of the three models, which have their own advantages and disadvantages. However, due to the size of the data set and the model itself, the effect is not very ideal, and still needs to be improved.

AB - Ancient poetry is an important part of Chinese culture. There have been projects like Jiuge to combine ancient poetry with deep learning. The language of ancient poetry is often refined, and it needs rich imagination to understand its meaning. As a result, it is difficult to automatically implement the translation. This paper makes a preliminary attempt in this aspect, based on the data set collected by ourselves, adopts deep encoder-decoder model, such as GRU, LSTM and Transformer models, to train our model. We compare the results of the three models, which have their own advantages and disadvantages. However, due to the size of the data set and the model itself, the effect is not very ideal, and still needs to be improved.

KW - Transformer

KW - ancient poetry

KW - deep learning

KW - machine translation

KW - natural language processing

KW - neural network

KW - seq2seq model

UR - https://www.scopus.com/pages/publications/85115444224

U2 - 10.1109/ICIEA51954.2021.9516256

DO - 10.1109/ICIEA51954.2021.9516256

M3 - 会议稿件

AN - SCOPUS:85115444224

T3 - Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021

SP - 2032

EP - 2036

BT - Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021

Y2 - 1 August 2021 through 4 August 2021

ER -

Boyuan W, Xiangli L, Hainan W, Baochang Z. A Comparative Study of Different Models in Ancient Poetry Translation. In Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2032-2036. (Proceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021). doi: 10.1109/ICIEA51954.2021.9516256

A Comparative Study of Different Models in Ancient Poetry Translation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this