Skripsi

ANSWER FINDING PADA INDONESIA QUESTION ANSWERING SYSTEM MENGGUNAKAN REGULAR EXPRESSION DAN COSINE SIMILARITY

---

A Question Answering System (QAS) is an automated system designed to provide accurate answers to questions posed using natural language. This research aims to determine the ability of the Indonesian QAS built to perform answer finding or predict the answers submitted to the system using regular expression and cosine similarity methods. The steps taken include filtering the system's documents that have the same type of interrogative word as the question submitted to the system using regular expression, after which the similarity value is calculated using cosine similarity. The system documents that have the highest similarity value to the question asked will be taken as the result of the system's answer finding. The system documents used consist of a collection of questions and answers divided into three types of interrogative words: 'what', 'who', and 'where', all themed around Indonesian history. The number of system documents is 150 pairs of questions and answers, consisting of 50 pairs for the 'what' type, 50 pairs for the 'who' type, and 50 pairs for the 'where' type. The system documents were obtained from websites and then documented in .sql file format. The system testing was conducted based on three scenarios, differentiated by the three types of interrogative words, in predicting the answers to 30 test questions for each scenario. The system resulted in an average precision(0.7), recall(0.7), and F-1 score(0.7) in predicting correct answers. In predicting answers, the system still predicted some incorrect answers, which is due to the number of words in the system documents being greater than the number of words in the questions asked.

---

Availability

Detail Information

Series Title

-

Call Number

T1532052024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xiv, 165 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Regular Expression

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment