Information Extraction from Web as Knowledge Resources for Indonesian Question Answering System

Abdiansah, Abdiansah; Utami, Alvi Syahrini

doi:10.2991/aisr.k.200424.064

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is research that makes a system model for the Open Domain Question and Answering System for Indonesian [13]. The model he made consists of three processes: preprocessing, information extraction processing, and text processing.…”

Section: Recent Workmentioning

confidence: 99%

See 1 more Smart Citation

Indonesian Information Extraction : Challenges and Opportunities

Puspitarani

2021

JATISI

View full text Add to dashboard Cite

Information extraction is part of natural language processing, aiming to find, retrieve, or process information. The data source for information extraction is text. Text cannot be separated from people's daily lives. Through text, a lot of confidential information can be obtained. To produce information, the unstructured text will be converted into structured data. There are many approaches that researchers take to this process. Most of the studies are in English. Therefore, this paper will present current research trends, challenges, and information extraction opportunities using Indonesian.

show abstract

Section: Recent Workmentioning

confidence: 99%

“…), and system infrastructure (network connection, processing unit, etc.) as modeled by Abdiansyah [13]. This system will be beneficial in education.…”

Section: Challenges and Opportunitiesmentioning

confidence: 99%

Indonesian Information Extraction : Challenges and Opportunities

Puspitarani

2021

JATISI

View full text Add to dashboard Cite

show abstract

A graph model with integrated pattern and query-based technique for extracting answer to questions in community question answering system

Ojokoh

Igbe

Afolabi

et al. 2023

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

In community question answering (CQA) systems, topical comments are very valuable to provide information for users. However, it becomes cumbersome going through all these in order to decipher the correct answers to particular questions.Hence, extracting a particular answer to a question becomes vital to avoid reading every comment in the forum. This paper is an extension of of our previous research work that extracted questions from an online forum to develop a system for answer extraction to questions. This system is based on a graph-based method by building answers for related questions using nKullback-Leibler (KL) divergence to obtain ranked answers to a question. The process of extracting answers to questions involves; question core, building question query, query-based answer extraction (QBAE), pattern-based answer extraction (PBAE), and combined answer extraction. The source data for this work were already existing data from ResearchGate, a socio-academic networking website that provides researchers the platform collaborate, ask question and offer answers to question. The performance for answer extraction for 2786 questions shows that when 80% of patterns and keywords were considered, QBAE and PBAE extracted 2765 and 2766 correct answers respectively, while the QBAE + PBAE method extracted 2782 correct answers. Also, when 90% of patterns and keywords were utilized, QBAE and PBAE extracted 2782 and 2784 correct answers, whereas the QBAE + PBAE method extracted 2786 correct answers. Our method was able to identify 229 questions without answers. Finally, the evaluation of our model reveals high-performance accuracy and precision.

show abstract

Information Extraction from Web as Knowledge Resources for Indonesian Question Answering System

Cited by 2 publications

References 5 publications

Indonesian Information Extraction : Challenges and Opportunities

Indonesian Information Extraction : Challenges and Opportunities

A graph model with integrated pattern and query-based technique for extracting answer to questions in community question answering system

Contact Info

Product

Resources

About