TY - GEN
T1 - Khmer POS Tagging Using Conditional Random Fields
AU - Sangvat, Sokunsatya
AU - Pluempitiwiriyawej, Charnyote
N1 - Publisher Copyright:
© 2018, Springer Nature Singapore Pte Ltd.
PY - 2018
Y1 - 2018
N2 - The transformation-based approach with hybrid of rule-based and tri-gram have already been introduced for Khmer part-of-speech (POS) tagging. In this study, in order to further explore this topic, we present an alternative approach to Khmer POS tagging using Conditional Random Fields (CRFs). Since the features greatly affect the tagging accuracy, we investigate five groups of features and use them with the CRF model. First, we study different contextual information and use it as our baseline model. We then analyze the characteristics of Khmer and come up with three additional groups of language-related features including morphemes, word-shapes and name-entities. We also explore the use of lexicon as features to further improve the accuracy of our tagger. Our proposed approach has been evaluated on a corpus of 41,058 words and 27 POS tags. The comparative study has shown that our proposed approach produces a competitive accuracy compared to other Khmer POS tagging approaches.
AB - The transformation-based approach with hybrid of rule-based and tri-gram have already been introduced for Khmer part-of-speech (POS) tagging. In this study, in order to further explore this topic, we present an alternative approach to Khmer POS tagging using Conditional Random Fields (CRFs). Since the features greatly affect the tagging accuracy, we investigate five groups of features and use them with the CRF model. First, we study different contextual information and use it as our baseline model. We then analyze the characteristics of Khmer and come up with three additional groups of language-related features including morphemes, word-shapes and name-entities. We also explore the use of lexicon as features to further improve the accuracy of our tagger. Our proposed approach has been evaluated on a corpus of 41,058 words and 27 POS tags. The comparative study has shown that our proposed approach produces a competitive accuracy compared to other Khmer POS tagging approaches.
KW - Conditional Random Fields
KW - Khmer
KW - POS tagging
KW - Part-of-speech tagging
UR - https://www.scopus.com/pages/publications/85044073164
U2 - 10.1007/978-981-10-8438-6_14
DO - 10.1007/978-981-10-8438-6_14
M3 - Conference contribution
AN - SCOPUS:85044073164
SN - 9789811084379
T3 - Communications in Computer and Information Science
SP - 169
EP - 178
BT - Computational Linguistics - 15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017, Revised Selected Papers
A2 - Pa, Win Pa
A2 - Hasida, Kôiti
PB - Springer Verlag
T2 - 15th International Conference of the Pacific Association for Computational Linguistics, PACLING 2017
Y2 - 16 August 2017 through 18 August 2017
ER -