Title
A corpus-based analysis of Filipino writing errors
Abstract
This study presents the common grammatical and spelling errors made by Filipino native speakers through corpus-based analysis. A total of 8,000 sentences of student translation exercises were collected and analyzed using manual and computational means. A total of 1,413 errors surfaced that were categorized into eight error types namely: use of ligatures, spelling error, use of enclitics, translation errors, hyphenation, use of function words “nang” and “ng”, morphophonemic errors, and word repetition. The study concludes that the top 3 common errors are the use of ligatures such as “na”, /-ng/ and /-g/ (46.6%), spelling errors such as incorrectly merging of different words (19.5%), and use of enclitics such as “daw” and “raw” (16.1%). For future works, theoretical framework will be considered when analyzing the errors.
Year
DOI
Venue
2016
10.1109/IALP.2016.7875943
2016 International Conference on Asian Language Processing (IALP)
Keywords
Field
DocType
Filipino Errors,Grammatical Errors,Spelling Errors,Filipino Syntax,Grammar Checker
Pragmatics,Computer science,Grammar,Morphophonology,Artificial intelligence,Spelling,Natural language processing,Merge (version control),Linguistics
Conference
ISSN
ISBN
Citations 
2159-1962
978-1-5090-0923-7
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Manolito Octaviano100.34
Matthew Phillip Go200.34
Allan Borra322.46
Nathaniel Oco455.24