Neural Morphological Segmentation Model for Mongolian

Weihua Wang; Rashel Fam; Feilong Bao; Yves Lepage; Guanglai Gao

doi:10.1109/IJCNN.2019.8852050

Neural Morphological Segmentation Model for Mongolian

Weihua Wang, Rashel Fam, Feilong Bao, Yves Lepage, Guanglai Gao

Graduate School of Information, Production and Systems

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

Abstract

Morphological segmentation is useful for processing Mongolian. In this paper, we manually build a morphological segmentation data set for Mongolian. We then present a character-based encoder-decoder model with attention mechanism to perform the morphological segmentation task. We further investigate the influence of analogy features extracted from scratch and improve the performance of our model using multi languages setting. Experimental results show that our encoder-decoder model with attention mechanism provides a strong baseline for Mongolian morphological segmentation. The analogy features provide useful information to the model and improve the performance of the system. The use of multi languages data set shows the capability of our model to acquire knowledge through different languages and delivers the best result.

Original language	English
Title of host publication	2019 International Joint Conference on Neural Networks, IJCNN 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728119854
DOIs	https://doi.org/10.1109/IJCNN.2019.8852050
Publication status	Published - 2019 Jul
Event	2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary Duration: 2019 Jul 14 → 2019 Jul 19

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2019-July

Conference

Conference	2019 International Joint Conference on Neural Networks, IJCNN 2019
Country	Hungary
City	Budapest
Period	19/7/14 → 19/7/19

Keywords

Encoder-Decoder model
Mongolian
Morphological Segmentation

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2019.8852050

Cite this

Wang, W., Fam, R., Bao, F., Lepage, Y., & Gao, G. (2019). Neural Morphological Segmentation Model for Mongolian. In 2019 International Joint Conference on Neural Networks, IJCNN 2019 [8852050] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2019.8852050

Neural Morphological Segmentation Model for Mongolian. / Wang, Weihua; Fam, Rashel; Bao, Feilong; Lepage, Yves; Gao, Guanglai.

2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8852050 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July).

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

Wang, W, Fam, R, Bao, F, Lepage, Y & Gao, G 2019, Neural Morphological Segmentation Model for Mongolian. in 2019 International Joint Conference on Neural Networks, IJCNN 2019., 8852050, Proceedings of the International Joint Conference on Neural Networks, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., 2019 International Joint Conference on Neural Networks, IJCNN 2019, Budapest, Hungary, 19/7/14. https://doi.org/10.1109/IJCNN.2019.8852050

@inproceedings{2c4bcbd66977428fa432659675d20be7,

title = "Neural Morphological Segmentation Model for Mongolian",

abstract = "Morphological segmentation is useful for processing Mongolian. In this paper, we manually build a morphological segmentation data set for Mongolian. We then present a character-based encoder-decoder model with attention mechanism to perform the morphological segmentation task. We further investigate the influence of analogy features extracted from scratch and improve the performance of our model using multi languages setting. Experimental results show that our encoder-decoder model with attention mechanism provides a strong baseline for Mongolian morphological segmentation. The analogy features provide useful information to the model and improve the performance of the system. The use of multi languages data set shows the capability of our model to acquire knowledge through different languages and delivers the best result.",

keywords = "Encoder-Decoder model, Mongolian, Morphological Segmentation",

author = "Weihua Wang and Rashel Fam and Feilong Bao and Yves Lepage and Guanglai Gao",

year = "2019",

month = jul,

doi = "10.1109/IJCNN.2019.8852050",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

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

booktitle = "2019 International Joint Conference on Neural Networks, IJCNN 2019",

note = "2019 International Joint Conference on Neural Networks, IJCNN 2019 ; Conference date: 14-07-2019 Through 19-07-2019",

}

TY - GEN

T1 - Neural Morphological Segmentation Model for Mongolian

AU - Wang, Weihua

AU - Fam, Rashel

AU - Bao, Feilong

AU - Lepage, Yves

AU - Gao, Guanglai

PY - 2019/7

Y1 - 2019/7

N2 - Morphological segmentation is useful for processing Mongolian. In this paper, we manually build a morphological segmentation data set for Mongolian. We then present a character-based encoder-decoder model with attention mechanism to perform the morphological segmentation task. We further investigate the influence of analogy features extracted from scratch and improve the performance of our model using multi languages setting. Experimental results show that our encoder-decoder model with attention mechanism provides a strong baseline for Mongolian morphological segmentation. The analogy features provide useful information to the model and improve the performance of the system. The use of multi languages data set shows the capability of our model to acquire knowledge through different languages and delivers the best result.

AB - Morphological segmentation is useful for processing Mongolian. In this paper, we manually build a morphological segmentation data set for Mongolian. We then present a character-based encoder-decoder model with attention mechanism to perform the morphological segmentation task. We further investigate the influence of analogy features extracted from scratch and improve the performance of our model using multi languages setting. Experimental results show that our encoder-decoder model with attention mechanism provides a strong baseline for Mongolian morphological segmentation. The analogy features provide useful information to the model and improve the performance of the system. The use of multi languages data set shows the capability of our model to acquire knowledge through different languages and delivers the best result.

KW - Encoder-Decoder model

KW - Mongolian

KW - Morphological Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85073235315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073235315&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2019.8852050

DO - 10.1109/IJCNN.2019.8852050

M3 - Conference contribution

AN - SCOPUS:85073235315

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2019 International Joint Conference on Neural Networks, IJCNN 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Joint Conference on Neural Networks, IJCNN 2019

Y2 - 14 July 2019 through 19 July 2019

ER -