Graduation Semester and Year
2019
Language
English
Document Type
Thesis
Degree Name
Master of Science in Computer Science
Department
Computer Science and Engineering
First Advisor
Vassilis Athitsos
Abstract
When extracting meaning from language, a common first step is to break down language into constituents, or words that work together as a unit. This task, known as parsing, typically follows a specific grammar in order decompose the language into its underlying structure composed of constituents. Difficulties with this grammar-based parsing occur, however, with real-world natural language due to its unstructured nature. Code-switching, the phenomenon of alternating between languages while communicating, further complicates this task by requiring us to parse based on two (or more) languages instead of one. In this thesis, a data-driven method to parse code-switched language into its constituents is presented. The code- switched language used in this thesis is Taglish, comprised of English and Tagalog, and the data is collected from the social media site Twitter.
Keywords
Language
Disciplines
Computer Sciences | Physical Sciences and Mathematics
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Qudah, Fadiah, "PARSING CODE-SWITCHED TAGLISH LANGUAGE BY CREATING CONSTITUENTS" (2019). Computer Science and Engineering Theses. 370.
https://mavmatrix.uta.edu/cse_theses/370
Comments
Degree granted by The University of Texas at Arlington