Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags

Van-Hai VU; Quang-Phuoc NGUYEN; Kiem-Hieu NGUYEN; Joon-Choul SHIN; Cheol-Young OCK

doi:10.1587/transinf.2019EDP7154

Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags

Van-Hai VU, Quang-Phuoc NGUYEN, Kiem-Hieu NGUYEN, Joon-Choul SHIN, Cheol-Young OCK

Full Text Views

0

Cite this

Summary :

Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.

Publication: IEICE TRANSACTIONS on Information Vol.E103-D No.4 pp.866-873

Publication Date: 2020/04/01

Publicized: 2020/01/15

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2019EDP7154

Type of Manuscript: PAPER

Category: Natural Language Processing

Authors

Van-Hai VU
  University of Ulsan
Quang-Phuoc NGUYEN
  University of Ulsan
Kiem-Hieu NGUYEN
  Hanoi University of Science and Technology
Joon-Choul SHIN
  University of Ulsan
Cheol-Young OCK
  University of Ulsan

Keyword

Korean-Vietnamese machine translation, neural machine translation, named entity recognition, part-of-speech, word sense disambiguation

Cite this

Copy

Van-Hai VU, Quang-Phuoc NGUYEN, Kiem-Hieu NGUYEN, Joon-Choul SHIN, Cheol-Young OCK, "Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags" in IEICE TRANSACTIONS on Information, vol. E103-D, no. 4, pp. 866-873, April 2020, doi: 10.1587/transinf.2019EDP7154.
Abstract: Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7154/_p

Copy

@ARTICLE{e103-d_4_866,
author={Van-Hai VU, Quang-Phuoc NGUYEN, Kiem-Hieu NGUYEN, Joon-Choul SHIN, Cheol-Young OCK, },
journal={IEICE TRANSACTIONS on Information},
title={Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags},
year={2020},
volume={E103-D},
number={4},
pages={866-873},
abstract={Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.},
keywords={},
doi={10.1587/transinf.2019EDP7154},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - Korean-Vietnamese Neural Machine Translation with Named Entity Recognition and Part-of-Speech Tags
T2 - IEICE TRANSACTIONS on Information
SP - 866
EP - 873
AU - Van-Hai VU
AU - Quang-Phuoc NGUYEN
AU - Kiem-Hieu NGUYEN
AU - Joon-Choul SHIN
AU - Cheol-Young OCK
PY - 2020
DO - 10.1587/transinf.2019EDP7154
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2020
AB - Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.
ER -