Why reinvent the wheel: Let's build question answering systems together

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

  • Kuldeep Singh
  • Arun Sethupat Radhakrishna
  • Andreas Both
  • Saeedeh Shekarpour
  • Ioanna Lytra
  • Ricardo Usbeck
  • Akhilesh Vyas
  • Akmal Khikmatullaev
  • Dharmen Punjani
  • Christoph Lange
  • Maria Esther Vidal
  • Jens Lehmann
  • Sören Auer

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.

Original languageEnglish
Title of host publicationThe Web Conference 2018 - Proceedings of the World Wide Web Conference, WWW 2018
EditorsPierre-Antoine Champin, Fabien Gandon, Lionel Medini
Number of pages10
PublisherAssociation for Computing Machinery, Inc
Publication date10.04.2018
Pages1247-1256
ISBN (print)978-1-4503-5639-8
DOIs
Publication statusPublished - 10.04.2018
Externally publishedYes
Event27th International World Wide Web, WWW 2018: Bridging natural and artificial intelligence worldwide - Universität Lyon, Lyon, France
Duration: 23.04.201827.04.2018
https://archives.iw3c2.org/www2018/

Bibliographical note

This work has received funding from the EU H2020 R&I programme for the Marie Skłodowska-Curie action WDAqua (GA No 642795), Eurostars project QAMEL (E!9725), and EU H2020 R&I HOBBIT (GA 688227). We thank Yakun Li, Osmar Zaiane, and Anant Gupta for their useful suggestions.

Publisher Copyright:
© 2018 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC BY 4.0 License.

DOI