Fine-Grained Named Entity Recognition for Sinhala

被引：0

作者：

Azeez, Rameela ^{[1
]}

Ranathunga, Surangika ^{[1
]}

机构：

[1] Univ Moratuwa, Dept Comp Sci & Engn, Katubedda 10400, Sri Lanka

来源：

MERCON 2020: 6TH INTERNATIONAL MULTIDISCIPLINARY MORATUWA ENGINEERING RESEARCH CONFERENCE (MERCON) | 2020年

关键词：

named entity recognition; sinhala; named entity; conditional random fields;

D O I：

10.1109/mercon50084.2020.9185296

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

For English, Named Entity Recognition (NER) is more or less a solved problem. However, for low-resourced and morphologically rich languages such as Sinhala, minimal research has been done. In this paper, we present a novel fine-grained Named Entity (NE) tag set and an NE annotated Sinhala corpus of 70k word tokens. We trained a custom NER model for Sinhala based on Conditional Random Fields (CRF). Despite the low-resourced setting, this NER model could achieve an micro-averaged F1 score of 84.8.

引用

页码：295 / 300

页数：6

共 24 条

[1] Akbik Alan, 2018, P 27 INT C COMPUTATI, P1638
[2] Curran James R., 2003, Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003-Volume, P164, DOI DOI 10.3115/1119176.1119200
[3] Dahanayaka JK, 2014, INT CONF ADV ICT, P215, DOI 10.1109/ICTER.2014.7083904
[4] Dai X, 2018, P ACL 2018 STUDENT R, P37
[5] De Meulder F., 2003, P 7 C NATURAL LANGUA, DOI DOI 10.3115/1119176.1119195
[6] Fernando A., 2020, INT C ADV ICT EM REG
[7] Fernando S, 2018, 2018 MORATUWA ENGINEERING RESEARCH CONFERENCE (MERCON) 4TH INTERNATIONAL MULTIDISCIPLINARY ENGINEERING RESEARCH CONFERENCE, P96, DOI 10.1109/MERCon.2018.8421997
[8] Fernando Sandareka, 2016, P 6 WORKSHOP S SE AS, P173
[9] Klie J.C., 2018, P 27 INT C COMP LING, P5
[10] Li JY, 2018, 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), P5794, DOI 10.1109/ICASSP.2018.8462017

← 1 2 3 →