scholarly journals A Natural Language Interface for Information Retrieval on Semantic Web Documents

Author(s):  
Paulo Quaresma ◽  
Irene Pimenta Rodrigues
2012 ◽  
Author(s):  
Arifah Che Alhadi ◽  
Shahrul Azman Noah ◽  
Lailatul Qadri Zakaria

Visi web semantik membolehkan capaian maklumat dilakukan secara semantik, yang mana model semantik kueri dipadankan dengan maklumat semantik dokumen web. Namun demikian kebanyakan dokumen web adalah tidak berstruktur dan tidak mempunyai maklumat semantik dokumen menyebabkan kesukaran proses pengkuerian. Oleh itu, capaian dan pengekstrakan maklumat semantik daripada dokumen web adalah amat penting dalam merealisasikan visi web semantik dan meningkatkan kualiti capaian maklumat. Kertas kerja ini membincangkan pengaplikasian pendekatan ontologi spesifik dan pemprosesan bahasa tabii dalam menyokong capaian dan pengekstrakan maklumat semantik dokumen web. Dengan menggunakan kedua-dua teknik ini, setiap kali capaian maklumat dilakukan, sistem akan menjana model integrasi semantik dokumen iaitu dokumen yang dicapai oleh enjin gelintar komersial yang ditetapkan. Model intergrasi semantik dokumen ini membolehkan pengguna mencapai dan melayarinya secara semantik. Hasil pengujian capaian dan padanan konsep yang dijalankan memperlihatkan kedua-dua teknik yang digunakan mampu mengenal pasti dan mengekstrak maklumat semantik daripada kueri dan kandungan dokumen web. Kata kunci: Capaian dokumen semantik, web semantik, ontologi, analisis bahasa tabii, perwakilan semantik dokumen, perwakilan semantik kueri The Semantic Web vision offers the potential to express queries in a more semantically way whereby semantic query model will be matched with semantic information of the document. However, the unstructured natures of existing web documents, which lack of semantic prove to be a difficult task for such a query. Therefore, semantic information retrieval and semantic information extraction of web documents content are important to realize semantic web vision and enhance the quality of information access. To support this, the semantic information content of web documents need to be specified in order to make the tangled information more structured and accessible. In this paper, we propose an approach meant to semantically query web documents using natural language analysis technique and a domain specific ontology. Using both techniques, the tool gradually constructs the semantic document integration model of the documents retrieved from an existing search engine for each search session. The semantic model can then be semantically refined and browsed by the user. The result of concept matching and accessing shows that both techniques that have been used could identify and extract semantic information from query and web document content. Key words: Semantic document retrieval, semantic web, ontology, natural language analysis, semantic document representation, semantic query representation


2016 ◽  
Vol 42 (6) ◽  
pp. 851-862 ◽  
Author(s):  
Mario Andrés Paredes-Valverde ◽  
Rafael Valencia-García ◽  
Miguel Ángel Rodríguez-García ◽  
Ricardo Colomo-Palacios ◽  
Giner Alor-Hernández

The semantic Web aims to provide to Web information with a well-defined meaning and make it understandable not only by humans but also by computers, thus allowing the automation, integration and reuse of high-quality information across different applications. However, current information retrieval mechanisms for semantic knowledge bases are intended to be only used by expert users. In this work, we propose a natural language interface that allows non-expert users the access to this kind of information through formulating queries in natural language. The present approach uses a domain-independent ontology model to represent the question’s structure and context. Also, this model allows determination of the answer type expected by the user based on a proposed question classification. To prove the effectiveness of our approach, we have conducted an evaluation in the music domain using LinkedBrainz, an effort to provide the MusicBrainz information as structured data on the Web by means of Semantic Web technologies. Our proposal obtained encouraging results based on the F-measure metric, ranging from 0.74 to 0.82 for a corpus of questions generated by a group of real-world end users.


IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 4233-4241
Author(s):  
Tian Bai ◽  
Yan Ge ◽  
Shuyu Guo ◽  
Zhenting Zhang ◽  
Leiguang Gong

Algorithms ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 217
Author(s):  
Haridimos Kondylakis ◽  
Dimitrios Tsirigotakis ◽  
Giorgos Fragkiadakis ◽  
Emmanouela Panteri ◽  
Alexandros Papadakis ◽  
...  

Chatbots, also known as conversation agents, are programs that are able to simulate and reproduce an intelligent conversation with humans. Although this type of program is not new, the explosion of the available information and the rapid increase of the users seeking this information have renewed the interest in their development. In this paper, we present R2D2, an intelligent chatbot relying on semantic web technologies and offering an intelligent controlled natural language interface for accessing the information available in DBpedia. The chatbot accepts structured input, allowing users to enter triple-pattern like queries, which are answered by the underlying engine. While typing, an auto-complete service guides users on creating the triple patterns, suggesting resources available in the DBpedia. Based on user input (in the form of triple-pattern like queries), the corresponding SPARQL queries are automatically formulated. The queries are submitted to the corresponding DBpedia SPARQL endpoint, and then the result is received by R2D2 and augmented with maps and visuals and eventually presented to the user. The usability evaluation performed shows the advantages of our solution and its usefulness.


Sign in / Sign up

Export Citation Format

Share Document