Architecture of an Ontology-Based Domain-Specific Natural Language Question Answering System

Athira, P M; Sreeja, M. U.; Raj, P. C. Reghu

doi:10.5121/ijwest.2013.4403

Cited by 26 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (Athira, Sreeja, & Reghuraj, 2013), it is presented a NLQA system for a specific domain based on the ontological information, a step towards SWQA. NL processing techniques are used for processing the question and documents and also for answer extraction.…”

Section: Related Workmentioning

confidence: 99%

Using a Dialogue Manager to Improve Semantic Web Search

Melo

Rodrigues

Nogueira

2016

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Question Answering systems that resort to the Semantic Web as a knowledge base can go well beyond the usual matching words in documents and, preferably, find a precise answer, without requiring user help to interpret the documents returned. In this paper, the authors introduce a Dialogue Manager that, through the analysis of the question and the type of expected answer, provides accurate answers to the questions posed in Natural Language. The Dialogue Manager not only represents the semantics of the questions, but also represents the structure of the discourse, including the user intentions and the questions context, adding the ability to deal with multiple answers and providing justified answers. The authors' system performance is evaluated by comparing with similar question answering systems. Although the test suite is slight dimension, the results obtained are very promising.

show abstract

Section: Related Workmentioning

confidence: 99%

Using a Dialogue Manager to Improve Semantic Web Search

Melo

Rodrigues

Nogueira

2016

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

show abstract

“…providing an answer or solution to a question that the user has. The use of semantic vocabularies to (re)formulate the question has been used previously in QandA systems, such as the systems created by Athira et al (2013) and Guo and Zhang (2008). Semantic technology becomes especially pertinent when the answers to the users' questions are also stored in semantic databases or on the semantic web (Bordes et al 2015).…”

Section: Related Workmentioning

confidence: 99%

“…In this sense, ask-Valerie has more in common with IR systems than with QandA systems. But unlike IR systems, the ask-Valerie system, does aim to provide the user with an exact answer, while IR systems typically provide the user with documents that are related to the answer (Athira et al 2013). …”

Section: Related Workmentioning

confidence: 99%

“…Athira et al (2013) compare QandA systems with Information Retrieval (IR) and Information Extraction (IE) systems in which a relevant subset of documents are found using IR by matching keywords provided by the user with an indexed set of words taken from the full set of documents. In this sense, ask-Valerie has more in common with IR systems than with QandA systems.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

From science to practice: Bringing innovations to agronomy and forestry

Willems¹,

Koenderink²,

Top³

2015

JAI

View full text Add to dashboard Cite

A B S T R A C TThe challenge of the work presented here is to make innovative research output in the agronomy and forestry domain accessible to end-users, so that it can be practically applied. We have developed an approach that consists of three key-elements: an ontology with domain knowledge, a set of documents that have been annotated and metaannotated, and a system (ask-Valerie) that is based on a dialogue to represent the interaction between end user and system. We show that the dialogue-metaphor is a good way of modelling the interaction between user and system. The system helps the user in formulating his question and in answering it in a useful way. Meta-annotations of key-paragraphs in the document-base turn out to be relevant in assessing in one glance what the content of a document is. End-users are very enthusiastic about the possibilities that ask-Valerie offers them in translating scientific results to their own situation.

show abstract

“…For example, MULDER [16] only accept questions entered in the English language and then submits them to Google; whereas AnswerBus [22] allows users to enter questions in German, French, Italian, and Portuguese , then translates them to English and submits them to more than one search Engine, HealthQA [21] which is a Chinese QA system for smart Health, AQuASys [10]. Instead of retrieving answers from the web, FAQ-Finder [18] uses files of frequently asked questions extracted from USENET News as its knowledge base, Athira et al, [9] describes an architecture of a semantic web question answering based on ontological information. However, the retrieving process for this is not that simple, as these systems use sophisticated language processing to analyse the user input and retrieve answers by applying grammar and semantic parsers.…”

Section: Introductionmentioning

confidence: 99%

A chatbot as a Question Answering Tool

2015

2015 International Conference on Advances in Software, Control and Mechanical Engineering (ICSCME'2015) Sept. 7-8, 2015 Antalya

View full text Add to dashboard Cite

Architecture of an Ontology-Based Domain-Specific Natural Language Question Answering System

Abstract: Question answering (QA)

Cited by 26 publications

References 9 publications

Using a Dialogue Manager to Improve Semantic Web Search

Using a Dialogue Manager to Improve Semantic Web Search

From science to practice: Bringing innovations to agronomy and forestry

A chatbot as a Question Answering Tool

Contact Info

Product

Resources

About