Question Answering Systems: Survey and Trends

Bouziane, Abdelghani; Bouchiha, Djelloul; Doumi, Noureddine; Malki, Mimoun

doi:10.1016/j.procs.2015.12.005

Cited by 107 publications

(46 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This study chose PerCorrect and MRR evaluation metrics since they reflect the accuracy of answers in QA systems, as both of them highlight different aspects of accuracy of answers in QA systems [7,48,49]. Since the objective of this study is to verify whether the inclusion of credibility scores (of Web pages) improves the accuracy of answers in Web-based QA systems, thus evaluation metrics concerning accuracy are chosen.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Web Pages Credibility Scores for Improving Accuracy of Answers in Web-Based Question Answering Systems

et al. 2020

View full text Add to dashboard Cite

Web-based question answering (QA) systems are effective in corroborating answers from multiple Web sources. However, Web also contains false, fabricated, and biased information that can have adverse effects on the accuracy of answers in Web-based QA systems. Existing, solutions focus primarily on finding relevant Web pages but either do not evaluate Web pages' credibility or evaluate two to three out of seven credibility categories. This research proposed a credibility assessment algorithm that uses seven categories, including correctness, authority, currency, professionalism, popularity, impartiality, quality, for scoring credibility, where each credibility category consists of multiple factors. The credibility assessment module is added on top of an existing QA system to score answers based on the credibility of Web pages. The system ranks answers based on the Web pages' credibility from where answers have been taken. The research conducted extensive quantitative tests on 211 factoid questions, taken from TREC QA data from 1999-2001. Our research findings show that credibility categories including correctness, professionalism, impartiality, and quality significantly improved the accuracy of answers. On the other hand, categories such as authority, currency, popularity played a minor role instead. This research hopes to allow researchers and experts in using the Web credibility assessment model to improve the accuracy of information systems. Credibility scores should assist Web users in selecting credible information, while also forcing content creators to focus more on publishing credible content.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Web Pages Credibility Scores for Improving Accuracy of Answers in Web-Based Question Answering Systems

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Based on different surveys ( [10], [11]), most of the NLIs that were developed in the recent years are based on English. They can be classified into close domain NLIs and open domain NLIs.…”

Section: Related Workmentioning

confidence: 99%

A Portable Natural Language Interface to Arabic Ontologies

Hakkoum¹,

Kharrazi²,

Raghay³

2018

ijacsa

View full text Add to dashboard Cite

With the growing expansion of the semantic web and its applications, providing natural language interfaces (NLI) to end-users becomes essential to querying RDF stores and ontologies, using simple questions expressed in natural language. Existing NLIs work mostly with the English language. There are very few attempts to develop systems supporting the Arabic language. In this paper, we propose a portable NLI to Arabic ontologies; it will transform the user's query expressed in Arabic into formal language query. The proposed system starts by a preparation phase that creates a gazetteer from the given ontology. The issued query is then processed using natural language processing (NLP) techniques to extract keywords. These keywords are mapped to the ontology entities, then a valid SPARQL query is generated based on the ontology definition and the reasoning capabilities of the Web Ontology Language (OWL). To evaluate our tool we used two different Arabic ontologies: a Qur'anic ontology and an Arabic sample of Mooney Geography dataset. The proposed system achieved 64% recall and 76% precision.

show abstract

“…Question Answer System is a system to find answers to human questions through input interfaces using natural language [1]. QAS implementation is mostly done in the form of input and output text rather than the sound [2,3], images or videos. Answer needs can be in the form of sentences, documents, pictures, sounds, or in the form of videos.…”

Section: Introductionmentioning

confidence: 99%

Integrated passage retrieval with fuzzy logic for Indonesian question answering system

Putra¹,

Nafâ€TMan²,

Gunawan³

2019

IJPCC

View full text Add to dashboard Cite

Question Answer System (QAS) has manymethods in determining candidate answer and must have theright answer for each question. Previous QAS using Fuzzylogic focused on candidate and ranking of answer. However,the QAS needs improvement in determining the relevantanswer from the question and generating the correct answer inthe question answer process. In this paper, we propose a newmethod to combine fuzzy logic and retrieval passages to obtaina collection of relevant answers in order to obtain high answeraccuracy. We take relevant answers from the collection of theanswer document and choose the exact answer using fuzzylogic. Methods for the QAS are preprocessing, questionanalyzer, passage retrieval, passage scoring, scoring for similartext, measuring keyword and candidate answers, fuzzy logiccontroller, rules, and extraction answer. This study producedsignificantly relevant answers compared to the TF-IDFmethod. The performance of the system has improved theaccuracy of QAS by 80% which is better than the previousstudy.

show abstract

Question Answering Systems: Survey and Trends

Cited by 107 publications

References 25 publications

Web Pages Credibility Scores for Improving Accuracy of Answers in Web-Based Question Answering Systems

Web Pages Credibility Scores for Improving Accuracy of Answers in Web-Based Question Answering Systems

A Portable Natural Language Interface to Arabic Ontologies

Integrated passage retrieval with fuzzy logic for Indonesian question answering system

Contact Info

Product

Resources

About