A corpus-based analysis of Filipino writing errors

Octaviano, Manolito; Go, Matthew Phillip; Borra, Allan; Oco, Nathaniel

doi:10.1109/ialp.2016.7875943

Cited by 2 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two categories of grammatical errors were covered by this study: (1) grammar errors and (2) spelling errors. These were derived from a book and previous studies that tackle Filipino grammatical errors (Komisyon sa Wikang Filipino, 2013;Octaviano et al, 2016).…”

Section: Covered Grammatical Errorsmentioning

confidence: 99%

“…• Morphological Errors. These are grammatical errors that may be caused by words that went through morphological changes (Octaviano et al, 2016). Due to various morphological processes, certain Filipino words alter their spelling.…”

Section: Grammar Errorsmentioning

confidence: 99%

“…These are spelling errors caused by mistakenly repeating a word that should not be repeated. Words such as ang 'the', ng 'of', and mga (denotes the plural form of a word) are some of the commonly duplicated words (Octaviano et al, 2016).…”

Section: Spelling Errorsmentioning

confidence: 99%

“…These are spelling errors caused by the wrong use of hyphenswhich may be used to separate prefixes from the base word. Hyphens are used when the base word is a proper noun, loan word, or starts with a vowel (Octaviano et al, 2016). For example, nag-usap is erroneously written as nagusap.…”

Section: Spelling Errorsmentioning

confidence: 99%

See 3 more Smart Citations

Balarila: Deep Learning for Semantic Grammar Error Correction in Low-Resource Settings

Ponce,

Jadie,

Espiritu

et al. 2023

Proceedings of the First Workshop in South East Asian Language Processing

View full text Add to dashboard Cite

While there are many grammar checkers available for various languages, especially the English language, those that exist for the lowresource Filipino language can only effectively correct lexical errors. There is yet to be a publicly available Filipino grammar checker that can also address semantic errors, which are more complex. As such, this study found an opportunity to introduce Balarila, a deep learning-based Filipino GEC model inspired by the GECToR approach. To address the absence of a training and test dataset, an automated error generation pipeline was devised, creating synthetic datasets of error-free and error-filled Filipino sentences sourced from various online news sources. Tagalog BERT and RoBERTa models were fine-tuned in two stages using this generated corpus. Evaluation metrics included precision, recall, and F 0.5 scores for GEC, and a multi-class confusion matrix for GED. The top-performing model, RoBERTa Tagalog Large, achieved an F 0.5 score of 70.75, while the RoBERTa Tagalog Base, with a F 0.5 score of 69.00, demonstrated cost-effectiveness in training. The created datasets can also be used as a benchmark for Filipino grammar checker models.

show abstract

Section: Covered Grammatical Errorsmentioning

confidence: 99%

Section: Grammar Errorsmentioning

confidence: 99%

Section: Spelling Errorsmentioning

confidence: 99%

Section: Spelling Errorsmentioning

confidence: 99%

See 2 more Smart Citations

Balarila: Deep Learning for Semantic Grammar Error Correction in Low-Resource Settings

Ponce,

Jadie,

Espiritu

et al. 2023

Proceedings of the First Workshop in South East Asian Language Processing

View full text Add to dashboard Cite

show abstract

Construcción de un corpus escrito y una ontología de errores ortográficos del chabacano zamboangueño

Himoro

Pareja-Lora

2023

RESLA

View full text Add to dashboard Cite

El chabacano zamboangueño es una lengua criolla filipina, de base española, hablada como lengua materna por más de 400.000 personas (datos de 2010). No obstante, su grafía normalizada es relativamente reciente (de 2014). Este artículo presenta una investigación destinada a la identificación y anotación semiautomática de los errores cometidos por sus hablantes al escribir, según la ortografía normativa. En primer lugar, detallamos los criterios aplicados en la construcción de un corpus de más de 8 millones de palabras del zamboangueño escrito y los géneros que lo componen, así como los formatos utilizados para codificarlo. En segundo lugar, describimos el proceso seguido para (1) el estudio de los errores y problemas ortográficos presentes en este corpus; (2) el desarrollo de una taxonomía elaborada para su mejor representación y clasificación; y (3) su formalización mediante una ontología. Por último, discutimos el resultado principal de este trabajo: un corpus de zamboangueño escrito, con sus errores ortográficos clasificados y anotados semiautomáticamente con enlaces a la ontología y sus formas corregidas correspondientes. Estas anotaciones nos permitirán a corto plazo analizar de manera más sistemática y profunda las faltas de ortografía cometidas por los usuarios del zamboangueño.

show abstract

A corpus-based analysis of Filipino writing errors

Cited by 2 publications

References 1 publication

Balarila: Deep Learning for Semantic Grammar Error Correction in Low-Resource Settings

Balarila: Deep Learning for Semantic Grammar Error Correction in Low-Resource Settings

Construcción de un corpus escrito y una ontología de errores ortográficos del chabacano zamboangueño

Contact Info

Product

Resources

About