Deep learning based parts of speech tagger for Bengali

Md Fasihul Kabir; Khandaker Abdullah-Al-Mamun; Mohammad Nurul Huda

doi:10.1109/ICIEV.2016.7760098

Deep learning based parts of speech tagger for Bengali

Md Fasihul Kabir, Khandaker Abdullah-Al-Mamun, Mohammad Nurul Huda

School of Science, Engineering & Technology (Harrisburg)

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

29 Scopus citations

Abstract

This paper describes the Part of Speech (POS) tagger for Bengali Language. Here, POS tagging is the process of assigning the part of speech tag or other lexical class marker to each and every word in a sentence. In many Natural Language Processing (NLP) applications, POS tagging is considered as the one of the basic necessary tools. Identifying the ambiguities in language lexical items is the challenging objective in the process of developing an efficient and accurate POS Tagger. Different methods of automating the process have been developed and employed for Bengali. In this paper, we report about our work on building POS tagger for Bengali using the Deep Learning. Bengali is a morphologically rich language and our taggers make use of morphological and contextual information of the words. It is observed from the experiments based on Linguistic Data Consortium (LDC) catalog number LDC2010T16 and ISBN 1-58563-561-8 corpus that 93.33% accuracy is obtained for Bengali POS tagger using the Deep Learning.

Original language	English (US)
Title of host publication	2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	26-29
Number of pages	4
ISBN (Electronic)	9781509012695
DOIs	https://doi.org/10.1109/ICIEV.2016.7760098
State	Published - Nov 28 2016
Event	5th International Conference on Informatics, Electronics and Vision, ICIEV 2016 - Dhaka, Bangladesh Duration: May 13 2016 → May 14 2016

Publication series

Name	2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016

Conference

Conference	5th International Conference on Informatics, Electronics and Vision, ICIEV 2016
Country/Territory	Bangladesh
City	Dhaka
Period	5/13/16 → 5/14/16

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Human-Computer Interaction
Information Systems
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/ICIEV.2016.7760098

Cite this

Kabir, M. F., Abdullah-Al-Mamun, K., & Huda, M. N. (2016). Deep learning based parts of speech tagger for Bengali. In 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016 (pp. 26-29). Article 7760098 (2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEV.2016.7760098

Kabir, Md Fasihul ; Abdullah-Al-Mamun, Khandaker ; Huda, Mohammad Nurul. / Deep learning based parts of speech tagger for Bengali. 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 26-29 (2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016).

@inproceedings{1cdb536f4f5d4702a3461cc9b752399f,

title = "Deep learning based parts of speech tagger for Bengali",

abstract = "This paper describes the Part of Speech (POS) tagger for Bengali Language. Here, POS tagging is the process of assigning the part of speech tag or other lexical class marker to each and every word in a sentence. In many Natural Language Processing (NLP) applications, POS tagging is considered as the one of the basic necessary tools. Identifying the ambiguities in language lexical items is the challenging objective in the process of developing an efficient and accurate POS Tagger. Different methods of automating the process have been developed and employed for Bengali. In this paper, we report about our work on building POS tagger for Bengali using the Deep Learning. Bengali is a morphologically rich language and our taggers make use of morphological and contextual information of the words. It is observed from the experiments based on Linguistic Data Consortium (LDC) catalog number LDC2010T16 and ISBN 1-58563-561-8 corpus that 93.33% accuracy is obtained for Bengali POS tagger using the Deep Learning.",

author = "Kabir, {Md Fasihul} and Khandaker Abdullah-Al-Mamun and Huda, {Mohammad Nurul}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016 ; Conference date: 13-05-2016 Through 14-05-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1109/ICIEV.2016.7760098",

language = "English (US)",

series = "2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016",

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

pages = "26--29",

booktitle = "2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016",

address = "United States",

}

Kabir, MF, Abdullah-Al-Mamun, K & Huda, MN 2016, Deep learning based parts of speech tagger for Bengali. in 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016., 7760098, 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016, Institute of Electrical and Electronics Engineers Inc., pp. 26-29, 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016, Dhaka, Bangladesh, 5/13/16. https://doi.org/10.1109/ICIEV.2016.7760098

Deep learning based parts of speech tagger for Bengali. / Kabir, Md Fasihul; Abdullah-Al-Mamun, Khandaker; Huda, Mohammad Nurul.
2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 26-29 7760098 (2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016).

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

TY - GEN

T1 - Deep learning based parts of speech tagger for Bengali

AU - Kabir, Md Fasihul

AU - Abdullah-Al-Mamun, Khandaker

AU - Huda, Mohammad Nurul

PY - 2016/11/28

Y1 - 2016/11/28

N2 - This paper describes the Part of Speech (POS) tagger for Bengali Language. Here, POS tagging is the process of assigning the part of speech tag or other lexical class marker to each and every word in a sentence. In many Natural Language Processing (NLP) applications, POS tagging is considered as the one of the basic necessary tools. Identifying the ambiguities in language lexical items is the challenging objective in the process of developing an efficient and accurate POS Tagger. Different methods of automating the process have been developed and employed for Bengali. In this paper, we report about our work on building POS tagger for Bengali using the Deep Learning. Bengali is a morphologically rich language and our taggers make use of morphological and contextual information of the words. It is observed from the experiments based on Linguistic Data Consortium (LDC) catalog number LDC2010T16 and ISBN 1-58563-561-8 corpus that 93.33% accuracy is obtained for Bengali POS tagger using the Deep Learning.

AB - This paper describes the Part of Speech (POS) tagger for Bengali Language. Here, POS tagging is the process of assigning the part of speech tag or other lexical class marker to each and every word in a sentence. In many Natural Language Processing (NLP) applications, POS tagging is considered as the one of the basic necessary tools. Identifying the ambiguities in language lexical items is the challenging objective in the process of developing an efficient and accurate POS Tagger. Different methods of automating the process have been developed and employed for Bengali. In this paper, we report about our work on building POS tagger for Bengali using the Deep Learning. Bengali is a morphologically rich language and our taggers make use of morphological and contextual information of the words. It is observed from the experiments based on Linguistic Data Consortium (LDC) catalog number LDC2010T16 and ISBN 1-58563-561-8 corpus that 93.33% accuracy is obtained for Bengali POS tagger using the Deep Learning.

UR - http://www.scopus.com/inward/record.url?scp=85007174596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007174596&partnerID=8YFLogxK

U2 - 10.1109/ICIEV.2016.7760098

DO - 10.1109/ICIEV.2016.7760098

M3 - Conference contribution

AN - SCOPUS:85007174596

T3 - 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016

SP - 26

EP - 29

BT - 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016

Y2 - 13 May 2016 through 14 May 2016

ER -

Kabir MF, Abdullah-Al-Mamun K, Huda MN. Deep learning based parts of speech tagger for Bengali. In 2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 26-29. 7760098. (2016 5th International Conference on Informatics, Electronics and Vision, ICIEV 2016). doi: 10.1109/ICIEV.2016.7760098

Deep learning based parts of speech tagger for Bengali

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this