A semantic-based question answering system for indonesian translation of Quran

Abstract

This paper presents a work in developing a semantic-based question answering system (QAS) for Indonesian Translation of Quran (ITQ). This research is motivated by the lacks of previous built QAS that caused by a keyword-based retrieval. Instead of keeping the retrieval method, we shifted to a semantic approach where the retrieval process is done by using a semantic similarity measurement. In doing so, we built an ontology of ITQ to get the concepts as well as verses where they appear in. We applied three factoid question types on the QAS that including Who, Where, and When. Furthermore, a weighted vector for each concept that belongs to respective expected answering type (also called as named entity group) i.e. Person, Location, and Time is generated in order to feed semantic interpreter on user question. From 222 concepts defined from the ontology, we clustered them into 77, 24, and 6 concepts for Person, Location, and Time respectively. Since we found there are some characteristics of texts in ITQ, we developed our own modules to deal with including generate the inverted index and named entity recognition. Answer extraction is conducted by applying some features extraction in order to score the answer candidates. Evaluation of the system is designed by providing two data set of question and answer where the first one is purposed to measure the effectiveness of semantic approach comparing with keyword-based retrieval and the last one aims to know system performance in regard the appearance of concepts in ITQ.

Analysis of K-means, DBSCAN and OPTICS Cluster Algorithms on Al-Quran Verses

“…The proposed method was called KCRA. Reference [12] developed a semantic-based question answering (QAS) for Indonesian Quran translation, which asked the users three questions, then created a TF-IDE for each term belonging to the respective expected response category (also called entity group) to feed or provide a semantic interpreter on user request. The author has organized 222 ontology principles into 6, 24, and 77 of Time, Position, and Individual concepts, respectively.…”

Integrated passage retrieval with fuzzy logic for Indonesian question answering system

“…So, the answer to the question in QAS is based on the strong relationship between the concept and the document using the weighted vector score. Second, Semantic Approach is used in the QAS [7]. According to Putra, et.al [12] the weight vector is combined with the semantic approach for selecting the best answer for the question in input system.…”

“…The method used by Putra, et. al [7] is Cosine similarity which is used to find the semantic from the question with the candidate answer in the ITQ dataset. The previous research of QAS in ITQ and Khulafaa AlRashidin dataset has one goal, which finds the exact answer from the candidate answer [5,7].…”

“…al [7] is Cosine similarity which is used to find the semantic from the question with the candidate answer in the ITQ dataset. The previous research of QAS in ITQ and Khulafaa AlRashidin dataset has one goal, which finds the exact answer from the candidate answer [5,7]. The architecture and technique to find the exact answers are various, from very simple architecture QAS using question analyzer, passage retrieval, and Name Entity recognizer [5], and then reconstruct the architecture with QAS2F to improve the answer using scoring of the candidate [13].…”

“…If the answer documents are widely available, the questions will be easily answered correctly, but if the opposite, the user has little or no right answer. QAS consists of various kinds of developing algorithms, like Fuzzy, weighted, ontology, artificial intelligence, Natural Language Processing (NLP) and Information Retrieval (IR) [6][7][8][9][10][11]. Some researchers also combine algorithms [1] to produce quality answers that are in accordance with the wishes of users.…”