NormAPI: An API for normalizing Filipino shortcut texts

Date of Publication

2014

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Charibeth K. Cheng

Defense Panel Chair

Ethel Chua Joy Ong

Defense Panel Member

Charibeth K. Cheng
Nathalie Rose Lim-Cheng
Allan B. Borra

Abstract/Summary

As the number of Internet and mobile phone users grows, texting and chatting have become popular means of communication. Reaching new heights, the extensive use of cellphones and Internet led into the creation of a new language, where words are transformed and made shorter using various styles. Shortcut texting is used all over the world and in recent years, numerous researchers have created normalization systems in different languages that would transform shortcut texts back into their original forms. This research designed techniques and developed NormAPI, a system that will normalize Filipino shortcut texts. Focused on modern Filipino language which includes code-switching, the system primarily contributes to Natural Language Processing (NLP) research as a preprocessing system that corrects informalities in shortcut texts before they are handed for complete data processing. Functionalities include using four normalization variations namely, Dictionary Substitution Approach (DSA), Statistical Machine Translation (SMT), SMT after DSA and SMT before DSA, with 0.68384, 0.79650, 0.75634 and 0.80750 BLEU scores, respectively. Additionally, options such as setting the dictionary, generating language models, getting BLEU scores and more can be utilized by users based on their preferences.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTU019260

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

leaves ; 4 3/4 in.

This document is currently not available here.

Share

COinS