LSVS: Link Specification Verbalization and Summarization
{. Ahmed, {. Sherif, und A. Ngonga Ngomo. 24th International Conference on Applications of Natural Language to Information Systems (NLDB 2019), Springer, (2019)
Zusammenfassung
An increasing number and size of datasets abiding by the Linked Data paradigm are published everyday. Discovering links between these datasets is thus central to achieve the vision behind the Data Web. Declarative Link Discovery (LD) frameworks rely on complex Link Specification (LS) to express the conditions under which two resources should
be linked. Understanding such LS is not a trivial task for non-expert users, particularly when such users are interested in generating LS to match their needs. Even if the user applies a machine learning algorithm for the automatic generation of the required LS, the challenge of explaining the resultant LS persists. Hence, providing explainable LS is the key
challenge to enable users who are unfamiliar with underlying LS technologies to use them effectively and efficiently. In this paper, we address this problem by proposing a generic approach that allows a LS to be verbalized, i.e., converted into understandable natural language. We propose a summarization approach to the verbalized LS based on the selectivity
of the underlying LS. Our adequacy and fluency evaluations show that our approach can generate complete and easily understandable natural language descriptions even by lay users.
%0 Conference Paper
%1 LSVS_2019
%A Ahmed, Abdullah Fathi
%A Sherif, Mohamed Ahmed
%A Ngonga Ngomo, Axel-Cyrille
%B 24th International Conference on Applications of Natural Language to Information Systems (NLDB 2019)
%D 2019
%I Springer
%K 2019 ahmed dice group_aksw limbo limes ngonga opal sage sherif simba slipo
%T LSVS: Link Specification Verbalization and Summarization
%U http://svn.aksw.org/papers/2019/NLDB_LSVS/public.pdf
%X An increasing number and size of datasets abiding by the Linked Data paradigm are published everyday. Discovering links between these datasets is thus central to achieve the vision behind the Data Web. Declarative Link Discovery (LD) frameworks rely on complex Link Specification (LS) to express the conditions under which two resources should
be linked. Understanding such LS is not a trivial task for non-expert users, particularly when such users are interested in generating LS to match their needs. Even if the user applies a machine learning algorithm for the automatic generation of the required LS, the challenge of explaining the resultant LS persists. Hence, providing explainable LS is the key
challenge to enable users who are unfamiliar with underlying LS technologies to use them effectively and efficiently. In this paper, we address this problem by proposing a generic approach that allows a LS to be verbalized, i.e., converted into understandable natural language. We propose a summarization approach to the verbalized LS based on the selectivity
of the underlying LS. Our adequacy and fluency evaluations show that our approach can generate complete and easily understandable natural language descriptions even by lay users.
@inproceedings{LSVS_2019,
abstract = {An increasing number and size of datasets abiding by the Linked Data paradigm are published everyday. Discovering links between these datasets is thus central to achieve the vision behind the Data Web. Declarative Link Discovery (LD) frameworks rely on complex Link Specification (LS) to express the conditions under which two resources should
be linked. Understanding such LS is not a trivial task for non-expert users, particularly when such users are interested in generating LS to match their needs. Even if the user applies a machine learning algorithm for the automatic generation of the required LS, the challenge of explaining the resultant LS persists. Hence, providing explainable LS is the key
challenge to enable users who are unfamiliar with underlying LS technologies to use them effectively and efficiently. In this paper, we address this problem by proposing a generic approach that allows a LS to be verbalized, i.e., converted into understandable natural language. We propose a summarization approach to the verbalized LS based on the selectivity
of the underlying LS. Our adequacy and fluency evaluations show that our approach can generate complete and easily understandable natural language descriptions even by lay users.},
added-at = {2024-03-04T14:13:36.000+0100},
author = {Ahmed, {Abdullah Fathi} and Sherif, {Mohamed Ahmed} and {Ngonga Ngomo}, Axel-Cyrille},
bdsk-url-1 = {http://svn.aksw.org/papers/2019/NLDB_LSVS/public.pdf},
biburl = {https://www.bibsonomy.org/bibtex/2a28d46aacfa164e596b353970b9cfbc1/aksw},
booktitle = {24th International Conference on Applications of Natural Language to Information Systems (NLDB 2019)},
interhash = {5b6172301568170f64fda907d09ce1f1},
intrahash = {a28d46aacfa164e596b353970b9cfbc1},
keywords = {2019 ahmed dice group_aksw limbo limes ngonga opal sage sherif simba slipo},
publisher = {Springer},
timestamp = {2024-03-04T14:13:36.000+0100},
title = {{LSVS}: Link Specification Verbalization and Summarization},
url = {http://svn.aksw.org/papers/2019/NLDB_LSVS/public.pdf},
year = 2019
}