Prapasha, Marandina Putri and , Husni Thamrin, M.T., Ph.D (2024) Implementasi Pos Tagging Dan Algoritma Antlr Parser Dalam Memeriksa Struktur Kalimat Bahasa Indonesia. Skripsi thesis, Universitas Muhammadiyah Surakarta.
![[img]](https://eprints.ums.ac.id/style/images/fileicons/application_pdf.png) |
PDF (Naskah Publikasi)
Marandina Putri Prapasha_L200200021_Naskah Publikasi Final.pdf Download (345kB) |
|
PDF (Surat Pernyataan Publikasi)
Srurat Pernyataan Publikasi Marandina Putri P.pdf Restricted to Repository staff only Download (470kB) |
Abstract
Communication is a step in which a message or information is conveyed from one party to another so that the message can be understood properly. Communication is a very important aspect for humans, not only in the realm of organizational life, but also in everyday life. Communication will run smoothly if the speaker uses language that is effective, structured and familiar to the person speaking. Effective language refers to the use of words that follow grammar or language rules properly and correctly, such as appropriate sentence structures or patterns. However, in general, many people do not pay attention to good and correct sentence structure in conveying their messages to other people. In the end, this has the potential to cause errors in language use. The aim of this research is to examine sentence structure by automatically identifying subjects, predicates, objects and adverbs (SPOK). Research is useful for making it easier to examine sentence structure. The method used is the application of the Flair algorithm for POS (Part Of Speech) Tagging and the ANTLR (ANother Tool Language Recognition) algorithm for parsing sentence structures. POS (Part Of Speech) Tagging is used to group words into certain categories such as nouns, verbs and adjectives. The ANTLR (ANother Tool Language Recognition) algorithm is used to determine the position of words or phrases as SPOK by using grammar and lexer to recognize tokens produced from the POS (Part Of Speech) Tagging process. The results of this research were that there were 424 correct sentences out of 500 sentences and produced a success rate (%) of 84.8%. A suggestion for future research is to take into consideration the use of a more complete and more accurate NLP library, as well as a wider corpus than the Flair NLP library used in this study, to determine word type labels. In addition, it is recommended to consider expanding the sentence structures used, not only limited to single sentences, but also include other types of sentences such as compound sentences and other types of sentences, so that sentence structures can be better examined and identified.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Sentence Structure, Parse, POS Tagging, ANTLR Parser |
| Subjects: | H Social Sciences > HE Communications |
| Divisions: | Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika |
| Depositing User: | MARANDINA PUTRI PRAPASHA |
| Date Deposited: | 18 May 2024 03:17 |
| Last Modified: | 18 May 2024 03:17 |
| URI: | http://eprints.ums.ac.id/id/eprint/124121 |
Actions (login required)
 |
View Item |
