Please use this identifier to cite or link to this item: https://oar.tib.eu/jspui/handle/123456789/5077
Files in This Item:
File SizeFormat 
Singh et al 2018, Why Reinvent the Wheel.pdf1,42 MBAdobe PDFView/Open
Title: Why reinvent the wheel: Let's build question answering systems together
Authors: Singh, K.Radhakrishna, A.S.Both, A.Shekarpour, S.Lytra, I.Usbeck, R.Vyas, A.Khikmatullaev, A.Punjani, D.Lange, C.Vidal, M.E.Lehmann, J.Auer, S.
Publishers Version: https://doi.org/10.1145/3178876.3186023
Issue Date: 2018
Published in: The Web Conference 2018 - Proceedings of the World Wide Web Conference, WWW 2018
Publisher: New York City : Association for Computing Machinery
Abstract: Modern question answering (QA) systems need to flexibly integrate a number of components specialised to fulfil specific tasks in a QA pipeline. Key QA tasks include Named Entity Recognition and Disambiguation, Relation Extraction, and Query Building. Since a number of different software components exist that implement different strategies for each of these tasks, it is a major challenge to select and combine the most suitable components into a QA system, given the characteristics of a question. We study this optimisation problem and train classifiers, which take features of a question as input and have the goal of optimising the selection of QA components based on those features. We then devise a greedy algorithm to identify the pipelines that include the suitable components and can effectively answer the given question. We implement this model within Frankenstein, a QA framework able to select QA components and compose QA pipelines. We evaluate the effectiveness of the pipelines generated by Frankenstein using the QALD and LC-QuAD benchmarks. These results not only suggest that Frankenstein precisely solves the QA optimisation problem but also enables the automatic composition of optimised QA pipelines, which outperform the static Baseline QA pipeline. Thanks to this flexible and fully automated pipeline generation process, new QA components can be easily included in Frankenstein, thus improving the performance of the generated pipelines.
Keywords: QA framework; Question answering; Semantic search; Semantic web; Software reusability; Natural language processing systems; Optimization; World Wide Web; Automatic composition; Generation process; Named entity recognition; Number of components; Optimisation problems; Question answering systems; Relation extraction; Software component; Pipelines
DDC: 004
License: CC BY 4.0 Unported
Link to License: https://creativecommons.org/licenses/by/4.0/
Appears in Collections:Informationswissenschaften



This item is licensed under a Creative Commons License Creative Commons