
		<paper>
			<loc>https://jjcit.org/paper/190</loc>
			<title>SEMANTIC RETRIEVAL FOR INDONESIAN QURAN AUTOCOMPLETION</title>
			<doi>10.5455/jjcit.71-1668279800</doi>
			<authors>Rian Adam Rajagede,Kholid Haryono,Rizan Qardafil</authors>
			<keywords>Semantic retrieval,Quran auto-completion</keywords>
			<citation>3</citation>
			<views>3614</views>
			<downloads>635</downloads>
			<received_date>7-Dec.-2022</received_date>
			<revised_date>  1-Feb.-2023 and 22-Feb.-2023</revised_date>
			<accepted_date>  5-Mar.-2023</accepted_date>
			<abstract>Attending  lectures  is  a  common  way  to  learn  Islamic knowledge.  The  speaker  talks  in  front  of  the  forum and 
participants take notes on the lecture material. Many participants listen to the lecture while taking notes either in 
books or on other digital devices to avoid forgetting the discussed topics. However, note-taking during the lecture 
can be challenging, with no complementing module from the speaker. Lecturers have different paces and varying 
ways of delivering. In addition, sometimes, participants cannot always focus during the lecture. Those factors can 
cause problems in the note-taking process: some details can be lost or even shift the meaning. For note-taking on 
sensitive topics, such as verses from the Quran, the note-taking process must be done carefully and avoid mistakes. 
In this study, we proposed an autocomplete system for the Indonesian translation of the Quran that will help the 
user in note-taking in Islamic lectures. The user writes down words, the parts of the Quran verse that he/she hears 
and the system will retrieve the most similar verses. With semantic retrieval, the user does not need to write down 
the exact words of the verses he/she heard. The system can also handle typographical-errors that usually occur in 
note-taking.  We  use  FastText  and  calculate  the  cosine  distance  between  the  query  and  verses  for  the  retrieval 
process.  We  also  performed  several  optimization  steps  to  create  a  robust  system  for  the  production  stage.  The 
system is evaluated by comparing how close the returned verse is with the ground truth. The proposed method's 
result in  terms  of accuracy  reached  70.59%  for  the  top  5  retrieved verses and 76.47%  for  the  top  10  retrieved 
verses.</abstract>
		</paper>


