Filters








95,330 Hits in 9.0 sec

Arabic Question Answering: A Study on Challenges, Systems, and Techniques

Heba Samy, Ehab E., Khaled Shaalan
2019 International Journal of Computer Applications  
The enormous increase of the amount of information available on the web creates the need for systems like Question Answering to bridge the gap between general end users and the web with its different data  ...  A general architecture is represented for the Question Answering task on both structured and unstructured data. Then, an overview of the work done in Arabic Question Answering Systems is presented.  ...  Fig 1 : 1 Fig 1: A QAS general architecture Fig 2 : 2 Fig 2: Phases of question answering system Fig 3 : 3 Fig 3: A general Architecture of QAS on Linked Data Table 1 Characterization of QA System  ... 
doi:10.5120/ijca2019918524 fatcat:zdncecxa4bhxnjnstdzyotkn3m

Question Answering Over Linked Data: What is Difficult to Answer? What Affects the F scores?

Muhammad Saleem, Samaneh Nazari Dastjerdi, Ricardo Usbeck, Axel-Cyrille Ngonga Ngomo
2017 International Semantic Web Conference  
We divide the QALD-6 questions into 8 main categories and compare state-of-the-art questions answering (QA) systems over Linked Data against the individual categories.  ...  We present a fine-grained analysis of the Question Answering over Linked Data (QALD-6) challenge.  ...  Once we know the general categories of the QALD-6 questions, next we want to investigate how QA systems over Linked Data perform across the different question categories?  ... 
dblp:conf/semweb/0002DUN17 fatcat:scq5gndd7vgjjavmf7jmgzgqrm

Automatic Inclusion of Semantics over Keyword-Based Linked Data Retrieval

Md-Mizanur RAHOMAN, Ryutaro ICHISE
2014 IEICE transactions on information and systems  
Md-Mizanur RAHOMAN †a) , Nonmember and Ryutaro ICHISE †, † †b) , Member SUMMARY Keyword-based linked data information retrieval is an easy choice for general-purpose users, but the implementation of such  ...  Then, we demonstrate how our proposal for automatic linked data information retrieval can be used alongside familiar keyword-based information retrieval methods, and can also be incorporated alongside  ...  For example, Unger et al. proposed a natural language based question answering (QA) system for linked data with Pythia [31] .  ... 
doi:10.1587/transinf.2014edp7073 fatcat:ijxwvktaxjhmdivmlzabq6in7i

QAKiS @ QALD-2

Elena Cabrio, Alessio Palmero Aprosio, Julien Cojan, Bernardo Magnini, Fabien Gandon, Alberto Lavelli
2012 Extended Semantic Web Conference  
We present QAKiS, a system for Question Answering over linked data (in particular, DBpedia).  ...  Wikipedia is used as the source of free text for the automatic extraction of the relational patterns, and DBpedia as the linked data resource to provide relational patterns and to be queried using a natural  ...  A crucial issue in Question Answering over linked data, and a major focus of the QAKiS system, is the interpretation of the question in order to convert it into a corresponding query in a formal language  ... 
dblp:conf/esws/CabrioACMGL12 fatcat:d77k7gfsybhzbpwmvtxigs2xpq

Robust question answering over the web of linked data

Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, Gerhard Weikum
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Knowledge bases and the Web of Linked Data have become important assets for search, recommendation, and analytics.  ...  Our system translates user questions into an extended form of structured SPARQL queries, with text predicates attached to triple patterns.  ...  As Yago and DBpedia entities reference each other via sameAs links, our slice of Linked Data combines the rich class system of Yago (with more than 300,000 classes including all of WordNet) with the extensive  ... 
doi:10.1145/2505515.2505677 dblp:conf/cikm/YahyaBEW13 fatcat:o7qklxaarvbqjcgjjxkprkzxfi

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs [article]

Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri, Jens Lehmann
2018 arXiv   pre-print
Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph.  ...  We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.  ...  Result: EARL performs better entity linking than the other systems (Table 5) , namely Babelfy, DBpediaSpotlight, TextRazor and AGDISTIS + FOX (limited to entity types -LOC, PER, ORG).  ... 
arXiv:1801.03825v4 fatcat:c27kwyclcbcf7nptvuvceucfeq

Evaluating Question Answering Over Linked Data

Vanessa Lopez, Christina Unger, Philipp Cimiano, Enrico Motta
2013 Social Science Research Network  
To address this gap, we have set up a series of evaluation challenges for question answering over linked data.  ...  The main goal of the challenge was to get insight into the strengths, capabilities and current shortcomings of question answering systems as interfaces to query linked data sources, as well as benchmarking  ...  In this paper we describe public evaluation challenges for question answering systems over linked data: QALD.  ... 
doi:10.2139/ssrn.3199070 fatcat:5ozki3gprnb4tdhcbt5srwiqrm

Evaluating question answering over linked data

Vanessa Lopez, Christina Unger, Philipp Cimiano, Enrico Motta
2013 Journal of Web Semantics  
To address this gap, we have set up a series of evaluation challenges for question answering over linked data.  ...  The main goal of the challenge was to get insight into the strengths, capabilities and current shortcomings of question answering systems as interfaces to query linked data sources, as well as benchmarking  ...  In this paper we describe public evaluation challenges for question answering systems over linked data: QALD.  ... 
doi:10.1016/j.websem.2013.05.006 fatcat:pm6ivyx5dzaphauenqfhcjnmnm

Question Answering System using Multiple Information Source and Open Type Answer Merge

Seonyeong Park, Soonchoul Kwon, Byungsoo Kim, Sangdo Han, Hyosup Shim, Gary Geunbae Lee
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations  
This paper presents a multi-strategy and multisource question answering (QA) system that can use multiple strategies to both answer natural language (NL) questions and respond to keywords.  ...  We develop open semantic answer type detector for answer merging and improve previous developed single QA modules such as knowledge base based QA, information retrieval based QA.  ...  Acknowledgments This work was supported by the ICT R&D program of MSIP/IITP [R0101-15-0176, Development of Core Technology for Human-like Selftaught Learning based on a Symbolic Approach].  ... 
doi:10.3115/v1/n15-3023 dblp:conf/naacl/ParkKKHSL15 fatcat:2jqfj44syvd3xev4fae56eep4i

6th Open Challenge on Question Answering over Linked Data (QALD-6) [chapter]

Christina Unger, Axel-Cyrille Ngonga Ngomo, Elena Cabrio
2016 Communications in Computer and Information Science  
The general task is the following one: Given a natural language question or keywords, retrieve the correct answer(s) from a given repository containing both RDF data and free text, in this case the English  ...  In future challenges we want also want to emphasize further aspects of question answering over linked data, such as querying data cubes, in order to continue to provide a state-of-the-art benchmark for  ... 
doi:10.1007/978-3-319-46565-4_13 fatcat:as3rmfpq3zcjde2mkmeo24x26a

A Semantic Question Answering through Heterogeneous Data Source in the Domain of Smart Factory

Orçun Oruç
2020 International Journal on Natural Language Computing  
Manufacturing technologies have evolved with advancements of Industry 4.0 about big data systems, generation system for linked data from unstructured data sources, and streaming data pools.  ...  Heterogeneous data source occurs adversity in converting linked data to get answers asked questions by human operators, experts, workers through question answering systems.  ...  ACKNOWLEDGEMENTS This work is funded by the German Research (DFG) within the Research Training Group Role-Based Software Infrastructures for continuous-context-sensitive Systems (GRK 1907).  ... 
doi:10.5121/ijnlc.2020.9403 fatcat:gcknl4k7yfhbbp5fkepycdtbpq

Using the weighted keyword model to improve information retrieval for answering biomedical questions

Hong Yu, Yong-Gang Cao
2009 Summit on translational bioinformatics  
Information retrieval systems that can provide immediate and relevant answers to these questions can be invaluable aids to the practice of evidence-based medicine.  ...  In this study, we first automatically identify topic keywords from ad hoc clinical questions with a Condition Random Field model that is trained over thousands of manually annotated clinical questions.  ...  Andrew Bennett for evaluating the AskHERMES system.  ... 
pmid:21347188 pmcid:PMC3041568 fatcat:5ehyqpvvozh2pcn63cdtjcnjru

ISOFT at QALD-5: Hybrid Question Answering System over Linked Data and Text Data

Seonyeong Park, Soonchoul Kwon, Byungsoo Kim, Gary Geunbae Lee
2015 Conference and Labs of the Evaluation Forum  
We develop a question answering system over linked data and text data.  ...  To reduce the number of converting NL phrases to words in KB, we extract clues of answers using IRQA and generate one SPARQL based on the extracted clues and analyses of the question and the semantic answer  ...  Recall, Precision report the measures with respect to the number of processed questions. F-1 Global reports the F-1 measure with respect to the total number of questions.  ... 
dblp:conf/clef/ParkKKL15 fatcat:vh56inpr3fdqdfhzxryxvwbzou

Artificial intelligence-based conversational agent to support medication prescribing

Anita M Preininger, Brett South, Jeff Heiland, Adam Buchold, Mya Baca, Suwei Wang, Rex Nipper, Nawshin Kutub, Bryan Bohanan, Gretchen Purcell Jackson
2020 JAMIA Open  
Conclusion WA enabled Micromedex users to obtain answers to many medication-related questions using natural language, with the conversational agent facilitating mapping to a broader distribution of topics  ...  Of the queries answerable by WA (288), SMEs determined 231 (80%) were correctly linked to an intent. Discussion A conversational agent successfully linked most queries to intents in Micromedex.  ...  In the conversation window, WA provides the adult dosing information for rivaroxaban with links to either "Quick Answers" or "In-Depth Answers" for rivaroxaban.  ... 
doi:10.1093/jamiaopen/ooaa009 pmid:32734163 pmcid:PMC7382615 fatcat:kzqk2ihnbfd3fbnz4aepdbecny

Systematic mapping study on question answering frameworks over linked data

Ceren Ocal Tasar, Murat Komesli, Murat Osman Unalir
2018 IET Software  
Employing linked data technologies and semantic endpoints for question answering systems are expanding approaches among the researchers.  ...  With a set of 14 research questions, inclusion and exclusion criteria are specified. 53 studies are selected as primary studies from an initial set of 845 papers.  ...  list for database search String Id Search string in title Full text Search string 1 Question answering question answering OR question answering systems Search string 2 Linked data linked data  ... 
doi:10.1049/iet-sen.2018.5105 fatcat:rategbtjjvcvherbpuphiivfiy
« Previous Showing results 1 — 15 out of 95,330 results