Implementasi Bidirectional Long Short Term Memory pada peringkasan abstraktif teks berbahasa Indonesia

Shaliha, Karima Marwazia (2021) Implementasi Bidirectional Long Short Term Memory pada peringkasan abstraktif teks berbahasa Indonesia. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (54kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (91kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (68kB) | Preview
	Text (BAB I) 4_bab1.pdf Restricted to Registered users only Download (155kB) | Request a copy
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (334kB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (508kB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (982kB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (24kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (167kB) | Request a copy

Abstract

The amount of text data on the internet is increasing, this is in line with the increasing development of text summarization. Text summarization developers are mostly oriented to extractive methods which have poor sentence structure. The abstraction method summary produces a more natural summary, but the process is more difficult than the extractive method. Bidirectional Long Short Term Memory (BiLSTM) shows a lot of success in abstracting abstraction of English texts. So, in this study, Bidirectional LSTM is used to improve the summary that is commonly developed, as well as the addition of Local Attention to assist the model in predicting the summary. The results of the evaluation of the model on the Indonesian language article text, the model can capture the essence of the source text as individual words with a value of ROUGE-1 0. 06236 and ROUGE-2 0. 00684.

Actions (login required)

View Item