Skripsi

WORD SENSE DISAMBIGUATION MENGGUNAKAN ALGORITMA SIMPLIFIED LESK PADA KALIMAT BAHASA INGGRIS

---

Penilaian

---

Every natural language has words that can have more than one meaning that could potentially cause doubt or ambiguity. This ambiguity can be an obstacle in communication causing differences in understanding. Therefore, a solution is needed to determine the meaning of ambiguous words in sentences so that they can be understood, namely Word Sense Disambiguation. The word sense disambiguation is carried out with the aim of identifying the right meaning, according to the context of the sentence. Various methods have been used for Word Sense Disambiguation, one of which is the Simplified Lesk algorithm. In this study, the data used were in the form of a collection of English sentences obtained from the FEWS website. The test was carried out on 500 data in the form of English sentences that have ambiguous words and their respective meanings which have been broken down into 100, 200, 300, 400 and 500 sentences. The test results on the Simplified Lesk algorithm only succeeded in determining the meaning of words less than 50% of the input sentences in the dataset. Where the results of the greatest accuracy are obtained when the number of input datasets is 100 sentences, which is 0.40. While the smallest accuracy results are obtained when the number of input datasets is 500 and 400 sentences, which is 0.34. And produce an average accuracy of 0.36.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002123	T54266	T542662021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T542662021

Publisher

Inderalaya : Fakultas Ilmu Komputer, Prodi Teknik Informatika., 2021

Collation

xvii, 79 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan Data, Teknik Informatika
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment