Benchmarking Mi-AR: Malay anaphora resolution

Benjamin Chu Min Xian; Mohammad Arshi Saloot; Amiera Syazreen Mohd Ghazali; Khalil Bouzekri; Rohana Mahmud; Dickson Lukose

doi:10.1109/OPTIP.2016.7528520

Benchmarking Mi-AR: Malay anaphora resolution

Benjamin Chu Min Xian
, Mohammad Arshi Saloot
, Amiera Syazreen Mohd Ghazali
, Khalil Bouzekri
, Rohana Mahmud
, Dickson Lukose

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

4 Citations (Scopus)

Abstract

This paper discusses benchmarking a new approach that uses the maximum entropy model and Random Forest classifier for pronominal anaphora resolution in the Malay language. Given the specific characteristics of the Malay language, such as gender-neutral pronouns, we pursued a specific two-phase methodology: (1) conducting analyses to scrutinize the features of Malay anaphors, and (2) designing, implementing, and evaluating a pronominal resolution system based on the analysis results. The approach achieved a 0.84 F-measure in testing with 9,779 tokens (i.e. 50 news and 50 non-news articles), and the results of our experiment and comparison study show that the presented approach significantly outperforms the current state-of-the-art Malay anaphora resolution systems.

Original language	English
Title of host publication	Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	59-69
Number of pages	11
ISBN (Electronic)	9781509008797
DOIs	https://doi.org/10.1109/OPTIP.2016.7528520
Publication status	Published - 2016
Externally published	Yes
Event	International Conference on Optoelectronics and Image Processing 2016 - Warsaw, Poland Duration: 10 Jun 2016 → 12 Jun 2016

Conference

Conference	International Conference on Optoelectronics and Image Processing 2016
Abbreviated title	ICOIP 2016
Country/Territory	Poland
City	Warsaw
Period	10/06/16 → 12/06/16

Keywords

anaphora resolution
benchmarking
Malay language
natural language processing

Access to Document

10.1109/OPTIP.2016.7528520

Cite this

Xian, B. C. M., Saloot, M. A., Ghazali, A. S. M., Bouzekri, K., Mahmud, R., & Lukose, D. (2016). Benchmarking Mi-AR: Malay anaphora resolution. In Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016 (pp. 59-69). Article 7528520 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/OPTIP.2016.7528520

@inproceedings{6347e763ec8d4648b01a5c1a3557238a,

title = "Benchmarking Mi-AR: Malay anaphora resolution",

abstract = "This paper discusses benchmarking a new approach that uses the maximum entropy model and Random Forest classifier for pronominal anaphora resolution in the Malay language. Given the specific characteristics of the Malay language, such as gender-neutral pronouns, we pursued a specific two-phase methodology: (1) conducting analyses to scrutinize the features of Malay anaphors, and (2) designing, implementing, and evaluating a pronominal resolution system based on the analysis results. The approach achieved a 0.84 F-measure in testing with 9,779 tokens (i.e. 50 news and 50 non-news articles), and the results of our experiment and comparison study show that the presented approach significantly outperforms the current state-of-the-art Malay anaphora resolution systems.",

keywords = "anaphora resolution, benchmarking, Malay language, natural language processing",

author = "Xian, \{Benjamin Chu Min\} and Saloot, \{Mohammad Arshi\} and Ghazali, \{Amiera Syazreen Mohd\} and Khalil Bouzekri and Rohana Mahmud and Dickson Lukose",

year = "2016",

doi = "10.1109/OPTIP.2016.7528520",

language = "English",

pages = "59--69",

booktitle = "Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "International Conference on Optoelectronics and Image Processing 2016, ICOIP 2016 ; Conference date: 10-06-2016 Through 12-06-2016",

}

Xian, BCM, Saloot, MA, Ghazali, ASM, Bouzekri, K, Mahmud, R & Lukose, D 2016, Benchmarking Mi-AR: Malay anaphora resolution. in Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016., 7528520, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 59-69, International Conference on Optoelectronics and Image Processing 2016, Warsaw, Poland, 10/06/16. https://doi.org/10.1109/OPTIP.2016.7528520

Benchmarking Mi-AR: Malay anaphora resolution. / Xian, Benjamin Chu Min; Saloot, Mohammad Arshi; Ghazali, Amiera Syazreen Mohd et al.
Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016. USA: IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 59-69 7528520.

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

TY - GEN

T1 - Benchmarking Mi-AR

T2 - International Conference on Optoelectronics and Image Processing 2016

AU - Xian, Benjamin Chu Min

AU - Saloot, Mohammad Arshi

AU - Ghazali, Amiera Syazreen Mohd

AU - Bouzekri, Khalil

AU - Mahmud, Rohana

AU - Lukose, Dickson

PY - 2016

Y1 - 2016

N2 - This paper discusses benchmarking a new approach that uses the maximum entropy model and Random Forest classifier for pronominal anaphora resolution in the Malay language. Given the specific characteristics of the Malay language, such as gender-neutral pronouns, we pursued a specific two-phase methodology: (1) conducting analyses to scrutinize the features of Malay anaphors, and (2) designing, implementing, and evaluating a pronominal resolution system based on the analysis results. The approach achieved a 0.84 F-measure in testing with 9,779 tokens (i.e. 50 news and 50 non-news articles), and the results of our experiment and comparison study show that the presented approach significantly outperforms the current state-of-the-art Malay anaphora resolution systems.

AB - This paper discusses benchmarking a new approach that uses the maximum entropy model and Random Forest classifier for pronominal anaphora resolution in the Malay language. Given the specific characteristics of the Malay language, such as gender-neutral pronouns, we pursued a specific two-phase methodology: (1) conducting analyses to scrutinize the features of Malay anaphors, and (2) designing, implementing, and evaluating a pronominal resolution system based on the analysis results. The approach achieved a 0.84 F-measure in testing with 9,779 tokens (i.e. 50 news and 50 non-news articles), and the results of our experiment and comparison study show that the presented approach significantly outperforms the current state-of-the-art Malay anaphora resolution systems.

KW - anaphora resolution

KW - benchmarking

KW - Malay language

KW - natural language processing

UR - https://www.scopus.com/pages/publications/84992161282

U2 - 10.1109/OPTIP.2016.7528520

DO - 10.1109/OPTIP.2016.7528520

M3 - Conference Paper

AN - SCOPUS:84992161282

SP - 59

EP - 69

BT - Proceedings of 2016 International Conference on Optoelectronics and Image Processing ICOIP 2016

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

Y2 - 10 June 2016 through 12 June 2016

ER -

Benchmarking Mi-AR: Malay anaphora resolution

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this