Filters








310 Hits in 8.7 sec

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph [article]

Kuldeep Singh and Ioanna Lytra and Arun Sethupat Radhakrishna and Saeedeh Shekarpour and Maria-Esther Vidal and Jens Lehmann
2020 arXiv   pre-print
Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question  ...  In this article, we analyse and micro evaluate the behaviour of 29 available QA components for DBpedia knowledge graph that were released by the research community since 2010.  ...  To the best of our knowledge, this is the first study over DBpedia with a high number of questions and components.  ... 
arXiv:1809.10044v2 fatcat:j2kwwva3xrcphi26gksuqrskfq

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [chapter]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2017 Lecture Notes in Computer Science  
The task of answering natural language questions over RDF data has received wIde interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  The task consists of mapping a natural language question to an executable form, e.g. SPARQL, so that answers from a given KB can be extracted.  ...  Acknowledgements This work was supported by the Cluster of Excellence Cognitive Interaction Technology 'CITEC' (EXC 277) at Bielefeld University, which is funded by the German Research Foundation (DFG)  ... 
doi:10.1007/978-3-319-68288-4_20 fatcat:y7bkqxj64zen7p656jkhmhrs5m

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [article]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2018 arXiv   pre-print
The task of answering natural language questions over RDF data has received wide interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  The task consists of mapping a natural language question to an executable form, e.g. SPARQL, so that answers from a given KB can be extracted.  ...  Acknowledgements This work was supported by the Cluster of Excellence Cognitive Interaction Technology 'CITEC' (EXC 277) at Bielefeld University, which is funded by the German Research Foundation (DFG)  ... 
arXiv:1802.09296v1 fatcat:e4oc3eadpnbkfifq4wu2kptcgq

Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition [article]

Anand Panchbhai and Tommaso Soru and Edgard Marx
2020 arXiv   pre-print
The aim of Question Answering systems is to allow lay users to access such data using natural language without needing to write formal queries.  ...  A booming amount of information is continuously added to the Internet as structured and unstructured data, feeding knowledge bases such as DBpedia and Wikidata with billions of statements describing millions  ...  The template generation methodology proposed here is for the DBpedia knowledge graph [7] . The first step deals with iterating over all the properties of a given class.  ... 
arXiv:2010.10900v1 fatcat:4agmhglkgvfkziiat3psob47oi

Benchmarking Knowledge Graphs on the Web [article]

Michael Röder and Mohamed Ahmed Sherif and Muhammad Saleem and Felix Conrads and Axel-Cyrille Ngonga Ngomo
2020 arXiv   pre-print
The growing interest in making use of Knowledge Graphs for developing explainable artificial intelligence, there is an increasing need for a comparable and repeatable comparison of the performance of Knowledge  ...  This paper gives an overview of benchmarks used to evaluate systems that process Knowledge Graphs.  ...  However, instead of answering a query based on a single RDF graph, they allow the querying of data from a single or over different versions of the graph (Fernández et al., 2019) .  ... 
arXiv:2002.06039v1 fatcat:tc25o6rplbekndjng4cqh2oxoe

Typing candidate answers using type coercion

J. W. Murdock, A. Kalyanpur, C. Welty, J. Fan, D. A. Ferrucci, D. C. Gondek, L. Zhang, H. Kanayama
2012 IBM Journal of Research and Development  
Our question-answering system is significantly more accurate with type coercion than it is without type coercion; these components have a combined impact of nearly 5% on the accuracy of the IBM Watsoni  ...  One popular approach to answering those questions is to develop recognizers to identify instances of common answer types (e.g., countries, animals, and food) and consider only answers on those lists.  ...  Subsequently, he joined the algorithms team on the DeepQA project and helped design the Watson question-answering system. Dr.  ... 
doi:10.1147/jrd.2012.2187036 fatcat:sdird2ikajcahox7gxksdzvaiu

A framework for real-time semantic social media analysis

Diana Maynard, Ian Roberts, Mark A. Greenwood, Dominic Rout, Kalina Bontcheva
2017 Journal of Web Semantics  
We plan to retrain the model on the latest release of DBpedia. The addition of YODIE in the toolkit, even if not perfect, enables us to enrich the search.  ...  Linking Open Data While a number of useful analyses can be performed over the raw processed data, the scope for discovering interesting connections is greatly widened when the data is made easily searchable  ... 
doi:10.1016/j.websem.2017.05.002 fatcat:q26kxj77cvff7ikmlgrzgccnve

A Framework for Real-Time Semantic Social Media Analysis

Diana Maynard, Ian Roberts, Mark A. Greenwood, Dominic Rout, Kalina Bontcheva
2017 Social Science Research Network  
We plan to retrain the model on the latest release of DBpedia. The addition of YODIE in the toolkit, even if not perfect, enables us to enrich the search.  ...  Linking Open Data While a number of useful analyses can be performed over the raw processed data, the scope for discovering interesting connections is greatly widened when the data is made easily searchable  ... 
doi:10.2139/ssrn.3199300 fatcat:vkf6xlpedjhtpn7cmtklkep3yi

LELA - A natural language processing system for Romanian tourism

Bernadette Varga, Alina Dia Trambitas-Miron, Andrei Roth, Anca Marginean, Radu Razvan Slavescu, Adrian Groza
2014 Proceedings of the 2014 Federated Conference on Computer Science and Information Systems  
We present the process of creating the linked data set, based on: i) engineering the LELA Romanian tourism ontology, and ii) populating the ontology by linking open data.  ...  The system also provides a natural language interface for the Romanian language. The queries are automatically translated into SPARQL based on a controlled vocabulary derived from the Lela ontology.  ...  ACKNOWLEDGEMENTS Part of this work was supported by the PN-II Innovation Checks of the Romanian Ministry of Research for supporting research in small and medium enterprises, through the project "LELA -  ... 
doi:10.15439/2014f323 dblp:conf/fedcsis/VargaTRMSG14 fatcat:kdk4g363kzgkdamyc6vdgr6ghe

Knowledge-based Conversational Search [article]

Svitlana Vakulenko
2019 arXiv   pre-print
Our results show that question answering is one of the key components required for efficient information access but it is not the only type of dialogue interactions that a conversational search system  ...  In the third research chapter, we propose a novel approach for complex question answering from a knowledge graph that surpasses the current state-of-the-art results in terms of both efficacy and efficiency  ...  The task of question answering over a knowledge graph (KGQA) is: given a natural language question Q and a knowledge graph K, produce the correct answer A, which is either a subset of entities in the KG  ... 
arXiv:1912.06859v1 fatcat:rab6kemqujflrobib7lvvy6hue

Rules for Inducing Hierarchies from Social Tagging Data [chapter]

Hang Dong, Wei Wang, Frans Coenen
2018 Lecture Notes in Computer Science  
Automatic generation of hierarchies from social tags is a challenging task.  ...  The learned hierarchies were compared to some of the widely used reference concept hierarchies.  ...  Third, we used three reference knowledge hierarchies (DBPedia, Microsoft Concept Graph and ACM Computing Classification System) to evaluate the quality of the learned hierarchies based on standard metrics  ... 
doi:10.1007/978-3-319-78105-1_38 fatcat:jifgrag63bfhrcqv7cnvhmlsca

Survey on English Entity Linking on Wikidata [article]

Cedric Möller, Jens Lehmann, Ricardo Usbeck
2021 arXiv   pre-print
Wikidata is a frequently updated, community-driven, and multilingual knowledge graph.  ...  This survey reveals that current Wikidata-specific Entity Linking datasets do not differ in their annotation scheme from schemes for other knowledge graphs like DBpedia.  ...  The authors also acknowledge the financial support by the Federal Ministry for Economic Affairs and Energy of Germany in the project CoyPu (project number 01MK21007G).  ... 
arXiv:2112.01989v1 fatcat:mq4w5jhwmrdvxdxduppab2pfwa

A Domain Independent Framework for Extracting Linked Semantic Data from Tables [chapter]

Varish Mulwad, Tim Finin, Anupam Joshi
2012 Lecture Notes in Computer Science  
Vast amounts of information is encoded in tables found in documents, on the Web, and in spreadsheets or databases.  ...  represent the inferred meaning as graph of RDF triples.  ...  Its goal is to judge the efficacy of drug dosages and treatments by performing meta-analyses (i.e systematic reviews) over published literature and clinical trials.  ... 
doi:10.1007/978-3-642-34213-4_2 fatcat:4zhdsin6ljhm7bqfacxidghlkm

A Case Study of NLG from Multimedia Data Sources: Generating Architectural Landmark Descriptions

Simon Mille, Leo Wanner, Spyridon Symeonidis, Maria Rousi, Montserrat Marimon Felipe, Klearchos Stavrothanasopoul, Petros Alvanitopoulos, Roberto Carlini
2020 Zenodo  
images; (iii) a retrieval component, which gathers relevant hproperty, subject, objecti triples from DBpedia; (iv) a fusion component, which stores the contents from the different modalities in a Knowledge  ...  We show that thanks to the addition of other modalities, we can make the verbalisation of DBpedia triples more relevant and/or inspiratio  ...  Acknowledgements This work was supported by the European Commission in the context of its H2020 Program under the grant numbers 870930-RIA, 779962-RIA, 825079-RIA, 786731-RIA at Universitat Pompeu Fabra  ... 
doi:10.5281/zenodo.4529236 fatcat:k36enq2vtfavnk3uyuwhb2oz4q

Building Watson: An Overview of the DeepQA Project

David Ferrucci, Eric Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya A. Kalyanpur, Adam Lally, J. William Murdock, Eric Nyberg, John Prager, Nico Schlaefer, Chris Welty
2010 The AI Magazine  
After 3 years of intense research and development by a core team of about 20 researches, Watson is performing at human expert-levels in terms of precision, confidence and speed at the Jeopardy!  ...  The extent of the challenge includes fielding a real-time automatic contestant on the show, not merely a laboratory exercise. The Jeopardy!  ...  It is this team who are responsible for the work described in this paper. From  ... 
doi:10.1609/aimag.v31i3.2303 fatcat:bqzu6kcak5gnhpabvyv6vuc7n4
« Previous Showing results 1 — 15 out of 310 results