Integrated passage retrieval with fuzzy logic for Indonesian question answering system


  • Syopiansyah Jaya Putra
  • Muhammad Zidny Naf’an
  • Muhamad Nur Gunawan



Question Answer System (QAS) has many
methods in determining candidate answer and must have the
right answer for each question. Previous QAS using Fuzzy
logic focused on candidate and ranking of answer. However,
the QAS needs improvement in determining the relevant
answer from the question and generating the correct answer in
the question answer process. In this paper, we propose a new
method to combine fuzzy logic and retrieval passages to obtain
a collection of relevant answers in order to obtain high answer
accuracy. We take relevant answers from the collection of the
answer document and choose the exact answer using fuzzy
logic. Methods for the QAS are preprocessing, question
analyzer, passage retrieval, passage scoring, scoring for similar
text, measuring keyword and candidate answers, fuzzy logic
controller, rules, and extraction answer. This study produced
significantly relevant answers compared to the TF-IDF
method. The performance of the system has improved the
accuracy of QAS by 80% which is better than the previous



How to Cite

Jaya Putra, S. ., Naf’an, M. Z., & Nur Gunawan, M. . (2019). Integrated passage retrieval with fuzzy logic for Indonesian question answering system. International Journal on Perceptive and Cognitive Computing, 5(2), 31-34.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.