Exploring Buhi corpus using natural language processing (NLP) /
Cortan, Jeed Leo G.,
Exploring Buhi corpus using natural language processing (NLP) / Jeed Leo G. Cortan, Khayzel L. Ricafort, and Jinky G. Villagracia. - 138 leaves.
Undergraduate Thesis (BSCS) - Computer Science.
Includes bibliographic references.
Buhi is a municipality located in the coastal province of Camarines Sur. It has 38
barangays and its residents speak a dialect called Buhinon, which is a blend of features
from the Bikol of Polangui, Albay, and the Iriga variant of Rinconada Bicol. Buhinon is
considered a lone language and is the only one used in Camarines Sur province. Because
of its unique and distinct dialect, researchers have proposed a study to develop a web-
based application that can translate Buhinon words into Filipino words, complete with corresponding speech tags and named entities. This will help non-native speakers, such as students, teachers, and researchers, to understand unfamiliar words. The proposed web- based application provides two functions for natural language processing (NLP): Filipino to Buhinon and Buhinon to Filipino. The researchers collected 1000 Buhinon words from San Pedro, San Pascual, and San Buena in Buhi, Camarines Sur as their dataset. To evaluate
the translation quality, the researchers used the BLEU score metric, which compares a
candidate’s translation with one or more reference translations. The researchers obtained
an average of 74 from the Buhinon reference and Tagalog reference translation. Studying
another culture based on their dialect is like building a relationship with the native speakers
and the people around the area. It’s an eye-opener to non-native speakers that someone’s
dialect will never be a barrier to anyone.
Exploring Buhi corpus using natural language processing (NLP) / Jeed Leo G. Cortan, Khayzel L. Ricafort, and Jinky G. Villagracia. - 138 leaves.
Undergraduate Thesis (BSCS) - Computer Science.
Includes bibliographic references.
Buhi is a municipality located in the coastal province of Camarines Sur. It has 38
barangays and its residents speak a dialect called Buhinon, which is a blend of features
from the Bikol of Polangui, Albay, and the Iriga variant of Rinconada Bicol. Buhinon is
considered a lone language and is the only one used in Camarines Sur province. Because
of its unique and distinct dialect, researchers have proposed a study to develop a web-
based application that can translate Buhinon words into Filipino words, complete with corresponding speech tags and named entities. This will help non-native speakers, such as students, teachers, and researchers, to understand unfamiliar words. The proposed web- based application provides two functions for natural language processing (NLP): Filipino to Buhinon and Buhinon to Filipino. The researchers collected 1000 Buhinon words from San Pedro, San Pascual, and San Buena in Buhi, Camarines Sur as their dataset. To evaluate
the translation quality, the researchers used the BLEU score metric, which compares a
candidate’s translation with one or more reference translations. The researchers obtained
an average of 74 from the Buhinon reference and Tagalog reference translation. Studying
another culture based on their dialect is like building a relationship with the native speakers
and the people around the area. It’s an eye-opener to non-native speakers that someone’s
dialect will never be a barrier to anyone.