A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
squall2sparql: a Translator from Controlled English to Full SPARQL 1.1
2013
Conference and Labs of the Evaluation Forum
Preserved Fulltext
This paper reports on the participation of the system squall2sparql in the QALD-3 question answering challenge for DBpedia. squall2sparql is a translator from SQUALL, a controlled natural language for ...
English, to SPARQL 1.1, a standard expressive query and update language for linked open data. ...
However, when such linguistic resources are available [12] , it is a shame not to use them, as they could improve recall, and make SQUALL sentences much more natural at the lexical level. ...
dblp:conf/clef/Ferre13
fatcat:eirjcn5pmbf6dbytcflarhk3he
Text correction algorithms for correct grammar and lexical errors in the English language
2020
Journal of Advances in Humanities and Social Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
A majority of search engines algorithms use the approach of error detection, which typically is not limited to a particular native language. ...
Thus, the syntax of English web search queries, the problem was identi ied by automatic speech recognition systems. ...
It aids in enhancing recall through query reformulation, and applies the use of part-of-speech tags to replace synonyms for words found in content, as well as part-of-speech tag for well-formed questions ...
doi:10.20474/jahss-6.3.2
fatcat:j5xhxqmqmfcjzdqk4ft4nscegy
Paraphrastic Reformulations in Spoken Corpora
[chapter]
2014
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Our work addresses the automatic detection of paraphrastic reformulation in French spoken corpora. The proposed approach is syntagmatic. ...
is seldom respected, as these usually belong to different syntactic categories. ...
For the automatic detection of paraphrastic reformulations, we can improve the current performance thanks to a better recognition of repetitions and to machine learning. ...
doi:10.1007/978-3-319-10888-9_42
fatcat:ulcelj65vjd5vljxiimajj5y44
CODA: Computer-aided ontology development architecture
2014
IBM Journal of Research and Development
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
allowing reuse of components developed inside UIMA framework to drive semi-automatic Acquisition of Knowledge from Web Content. ...
This paper provides a first overview of the whole picture, and introduces UIMAST, an extension for the Knowledge Management and Acquisition Platform Semantic Turkey, that implements CODA principles by ...
We hope that the ongoing realization of CODA will lead to a more mature support for research in the fields of both ontology learning and ontology/lexicon interfaces, .
References ...
doi:10.1147/jrd.2014.2307518
fatcat:mpcdj75vvjhxdgejskw7eqwy54
Research and Reviews in Question Answering System
2013
Procedia Technology - Elsevier
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose taxonomy for characterizing Question Answer (QA) systems, briefly survey major QA systems described in literature and provide a qualitative analysis of them. ...
The fundamental thought behind QA system is to assist man-machine interaction. ...
In some of the recent linguistic approach based systems, web is used as the knowledge resource for local knowledge base, which not only led to enhanced knowledge within the domain but paved the way for ...
doi:10.1016/j.protcy.2013.12.378
fatcat:6px3nuaha5h4zh53ae6oyt4yei
An Ontology Based Framework for Automatic Web Resources Identification
2020
International Journal of Intelligent Engineering and Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a model for improving the search engines capabilities through adding level of awareness to the web resources. ...
This may be due to the huge number of web resources, the lack of search keywords for specific domains, and the gap between the user and author in specific domain. ...
It considers user's annotations as part of web resource index, then analyze them syntactically and semantically in order to map them to web resources automatically. ...
doi:10.22266/ijies2020.0430.29
fatcat:yx6bgylmszfzhkowotfd65jkb4
AquaLog: An ontology-driven question answering system for organizational semantic intranets
2007
Journal of Web Semantics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Moreover it also includes a learning component, which ensures that the performance of the system improves over the time, in response to the particular community jargon used by end users. ...
We say that AquaLog is portable because the configuration time required to customize the system for a particular ontology is negligible. ...
lexical resources such as WordNet, and a domain-dependent lexicon obtained through the use of a Learning Mechanism, explained in Section 5.5. ...
doi:10.1016/j.websem.2007.03.003
fatcat:dmamxd6kx5bs7d5hxsv3ngksh4
Aqualog: An Ontology-Driven Question Answering System for Organizational Semantic Intranets
2007
Social Science Research Network
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Moreover it also includes a learning component, which ensures that the performance of the system improves over the time, in response to the particular community jargon used by end users. ...
We say that AquaLog is portable because the configuration time required to customize the system for a particular ontology is negligible. ...
lexical resources such as WordNet, and a domain-dependent lexicon obtained through the use of a Learning Mechanism, explained in Section 5.5. ...
doi:10.2139/ssrn.3199356
fatcat:kt2t2iqn6vb3lbd3oilcylhsnu
Query-driven approach of contextual ontology module learning using web snippets
2013
Journal of Intelligent Information Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
And for each reformulation, we get
automatically a set of 30 to 50 snippets. ...
A study of several available types of search engines on the web has
been carried out in order to be used in the learning process (searches web resources
and calculates a score based on the number of hits ...
doi:10.1007/s10844-013-0263-6
fatcat:4utgwwlim5ct5jbztykqvsc3u4
Human-computer interaction
2012
Proceedings of the 24th Australian Computer-Human Interaction Conference on - OzCHI '12
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper discusses users' query reformulation behaviour while searching information on the Web. ...
Query reformulations have emerged as an important component of Web search behaviour and humancomputer interaction (HCI) because a user's success of information retrieval (IR) depends on how he or she formulates ...
Rieh and Xie (2006) characterized Web query reformulation as having three facets: content, format and resource. ...
doi:10.1145/2414536.2414586
dblp:conf/ozchi/KinleyTPE12
fatcat:lastwb6tcnbmvczjaarewa6wbm
Multiple-Engine Question Answering in TextMap
2003
Text Retrieval Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
TextMap uses a slightly cleaned-up version of Michael Fleischman's list of 966,557 descriptor entries for proper people (Fleischman et al., 2003) such as 10 composer , composer , composer , Aaron Copland ...
"Aaron Copland") has a WordNet gloss (Miller and Fellbaum, 1998), TextMap gives credit for sentences that contain words and expressions that overlap with that WordNet gloss (as underlined in the example ...
Collection of Descriptors for Proper People ...
dblp:conf/trec/EchihabiHHMMR03
fatcat:3wszgzzhnjeg7efubnyxdll3ee
Information Searching Tactics of Web Searchers
2007
Proceedings of the American Society for Information Science and Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper examines patterns and features of query reformulation within a Web searching session. ...
Then, we analyzed these sessions for query reformulation tactics that the searcher employed. ...
Then, people's searching process could be viewed as a learning process. People have begun to learn as soon as they are born to the world. ...
doi:10.1002/meet.14504301105
fatcat:dst4vn66dvehpixrpawoqasdb4
Improving the performance of question answering with semantically equivalent answer patterns
2008
Data & Knowledge Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit the original URL.
The file type is application/pdf.
First, we present a method for acquiring semantic-based reformulations automatically. ...
The evaluation on 493 questions from TREC-11 shows that the automatically acquired semantic patterns increase the MRR by 26%, the re-ranking using semantic redundancy increases the MRR by 67%, and the ...
The authors would like to thank the anonymous referees for their valuable comments. ...
doi:10.1016/j.datak.2007.07.010
fatcat:ucrojdvvunfariengmizqo6vlm
A Model-Driven Approach of Ontological Components for On-line Semantic Web Information Retrieval
2007
Journal of Web Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The objective of the paper is to propose a solution for the representation of Web knowledge by means of ontologies as well as to define an approach to their semi-automatic construction. ...
Ontologies specify the knowledge shared by a community of a target domain in an explicit and formal way. The present work deals with the problem of ontology construction for the Semantic Web. ...
The input data is constituted by linguistic resources such as a list of terms and relationships. ...
dblp:journals/jwe/ZghalAM07
fatcat:rffmi3crevdh5njfl6nxtur6ia
Comparison of Question Answering Systems Based on Ontology and Semantic Web in Different Environment
2012
Journal of Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Our question answering for automatic learning system architecture is used to overcome the difficulties raised from the different QA models. ...
Our system successfully implements this technique and the system is also used in intelligent manner for automatic learning method. ...
Resource Description Framework (RDF) is a framework to annotate information resources in a machine-understandable way. It is used for making statements rather than language itself. ...
doi:10.3844/jcssp.2012.1407.1413
fatcat:xdfchvwntrfjxemyw6z5nogwvm
« Previous
Showing results 1 — 15 out of 4,608 results