Dbpedia Based Factoid Question Answering System

Tahri, Adel; Tibermacine, Okba

doi:10.5121/ijwest.2013.4303

Cited by 22 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There is a need to develop accurate systems for automated question answering as there are a lot of structured knowledge-bases and the continuous demand to access information rapidly and efficiently. In [5], a Dbpedia based factoid question-answering system is…”

Section:  Machine Learning Applicationsmentioning

confidence: 99%

Using Big Data Technique for Building Edit Alert System for Wikipedia Infoboxes Based on Map-Reduce Method

Bhatia¹,

Halder²,

Yadav³

et al. 2018

IJIRCST

View full text Add to dashboard Cite

Wikipedia is an online encyclopedia and has become a vital information resource for users as well as for many knowledge bases derived from it. This information requires manual editing for update. Wikipedia provides an infobox on the right hand side of many articles. An infobox of a Wikipedia article generally contains key facts in thearticle and is organized as attribute-value pairs. All the Wikipedia's content is manually updated or maintained by contributors. This leads to the fact that its information is not updated regularly and completely. In this paper, we present a novel system that focuses onprediction of data items that are most likely to be updated, based on the category of page, record key, last time updated, etc. for alerting Wikipedia editors, about the data items that might need update soon, using Time series modeling. Concept of Bipartite graph is used to perform user based collaborative filtering to find similar editors who might be interested in editing the infobox. The update alert is sent to editors found using Bipartite graph along with the past editors of a particular infobox. The technique to deal with vandalic and erroneous edits is also discussed and its analysis is given. We have also presented various tasks that can be carried out on infoboxes.

show abstract

Section:  Machine Learning Applicationsmentioning

confidence: 99%

Using Big Data Technique for Building Edit Alert System for Wikipedia Infoboxes Based on Map-Reduce Method

Bhatia¹,

Halder²,

Yadav³

et al. 2018

IJIRCST

View full text Add to dashboard Cite

show abstract

“…The main motivation behind this work was to devise a way to utilize the existing semi-structured, large-size Wikipedia database as a knowledge source for a QA system without building high-cost knowledge base. [1] For semi-structured knowledge-bases QA System [2], a new architecture to develop a factoid question answering system based on the DBpedia ontology and the DBpedia extraction framework. Dbpedia is a project that aims at extracting information based on the semi-structured data presented within the Wikipedia articles.…”

Section: Classmentioning

confidence: 99%

“…This system is divided into three parts as Question Classification and Decision Model Generation, Question Processing and Query Formulation and Execution. This paper [2] is divided into 3 parts as Question Classification and Decision Model Generation, Question Processing and Query Formulation and Execution.…”

Section: Classmentioning

confidence: 99%

“…(i) Question Classification and Decision Model Generation: It is given by two components; first component is the question classifier which pre-processes the question dataset and trains it by the SVM algorithm [2], [11] which is a binary classifier giving two classes as the coarse-grained classes and the fine-grained classes for their proposed QA System. And the second component is the decision model generator which fallows tokenization, stop words removal and features extraction using the bag of words.…”

Section: Classmentioning

confidence: 99%

See 1 more Smart Citation

Keywords based Closed Domain Question Answering System for Indian Penal Code Sections and Indian Amendment Laws

Kamdi¹,

Agrawal²

2015

IJISA

View full text Add to dashboard Cite

In information retrieval, Question Answering (QA) is the task of answering a question posed in natural language (NL) using either a pre-structured database or a collection of natural language documents without human intervention. Question Answering systems are categorized on their available resource for answers. The domain specific Question Answering System gives more exact and correct answers than web based Question Answering system as it is limited for only one domain resource to answer. This paper proposes the closed domain Question Answering System for handling the legal documents of Indian Penal Code (IPC) sections and Indian Amendment Laws to retrieve more precise answers. This system tries to retrieve the exact answers from stored knowledge-base for the query related to Indian Penal Code (IPC) sections and Indian Amendment Laws asked by user. This Keyword based Question Answering System works on structured, unstructured and non-question form queries. The closed domain Question Answering system gives more accurate answer than other open domain system as it restricted single resource. Keywords from both queries and answer corpus play important role for extracting answer.

show abstract

“…Tahri, Adel, and Okba Tibermacine [10] have proposed a new architecture to develop a factoid question answering system based on the DBPedia ontology and the DBPedia extraction framework. There system SELNI is a sentence level question answering system that integrates natural language processing, ontologies, machine learning and information retrieval techniques.…”

Section: Related Workmentioning

confidence: 99%