Plumber: A Modular Framework to Create Information Extraction Pipelines

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Mohamad Yaser Jaradeh
  • Kuldeep Singh
  • Markus Stocker
  • Sören Auer

Research Organisations

External Research Organisations

  • German National Library of Science and Technology (TIB)
  • Zerotha-Research and Cerence GmbH
View graph of relations

Details

Original languageEnglish
Title of host publicationThe Web Conference 2021
Subtitle of host publicationCompanion of the World Wide Web Conference, WWW 2021
Pages678-679
Number of pages2
ISBN (electronic)9781450383134
Publication statusPublished - 19 Apr 2021
EventWorld Wide Web Conference (WWW 2021) - Ljubljana, Slovenia
Duration: 19 Apr 202123 Apr 2021
Conference number: 30

Abstract

Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present Plumber , the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online1.

Keywords

    Information Extraction, NLP Pipelines, Semantic Web, Software Reusability

ASJC Scopus subject areas

Cite this

Plumber: A Modular Framework to Create Information Extraction Pipelines. / Jaradeh, Mohamad Yaser; Singh, Kuldeep; Stocker, Markus et al.
The Web Conference 2021 : Companion of the World Wide Web Conference, WWW 2021. 2021. p. 678-679.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Jaradeh, MY, Singh, K, Stocker, M & Auer, S 2021, Plumber: A Modular Framework to Create Information Extraction Pipelines. in The Web Conference 2021 : Companion of the World Wide Web Conference, WWW 2021. pp. 678-679, World Wide Web Conference (WWW 2021), Ljubljana, Slovenia, 19 Apr 2021. https://doi.org/10.48550/arXiv.2206.01442, https://doi.org/10.1145/3442442.3458603
Jaradeh, M. Y., Singh, K., Stocker, M., & Auer, S. (2021). Plumber: A Modular Framework to Create Information Extraction Pipelines. In The Web Conference 2021 : Companion of the World Wide Web Conference, WWW 2021 (pp. 678-679) https://doi.org/10.48550/arXiv.2206.01442, https://doi.org/10.1145/3442442.3458603
Jaradeh MY, Singh K, Stocker M, Auer S. Plumber: A Modular Framework to Create Information Extraction Pipelines. In The Web Conference 2021 : Companion of the World Wide Web Conference, WWW 2021. 2021. p. 678-679 doi: 10.48550/arXiv.2206.01442, 10.1145/3442442.3458603
Jaradeh, Mohamad Yaser ; Singh, Kuldeep ; Stocker, Markus et al. / Plumber : A Modular Framework to Create Information Extraction Pipelines. The Web Conference 2021 : Companion of the World Wide Web Conference, WWW 2021. 2021. pp. 678-679
Download
@inproceedings{0fe68f40641f403bb1e4984de2054c80,
title = "Plumber: A Modular Framework to Create Information Extraction Pipelines",
abstract = "Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present Plumber , the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online1.",
keywords = "Information Extraction, NLP Pipelines, Semantic Web, Software Reusability",
author = "Jaradeh, {Mohamad Yaser} and Kuldeep Singh and Markus Stocker and S{\"o}ren Auer",
note = "Funding Information: This work was co-funded by the European Research Council for the project Science GRAPH (Grant agreement ID: 819536) and the TIB Leibniz Information Centre for Science and Technology.; World Wide Web Conference (WWW 2021), WWW 2021 ; Conference date: 19-04-2021 Through 23-04-2021",
year = "2021",
month = apr,
day = "19",
doi = "10.48550/arXiv.2206.01442",
language = "English",
pages = "678--679",
booktitle = "The Web Conference 2021",

}

Download

TY - GEN

T1 - Plumber

T2 - World Wide Web Conference (WWW 2021)

AU - Jaradeh, Mohamad Yaser

AU - Singh, Kuldeep

AU - Stocker, Markus

AU - Auer, Sören

N1 - Conference code: 30

PY - 2021/4/19

Y1 - 2021/4/19

N2 - Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present Plumber , the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online1.

AB - Information Extraction (IE) tasks are commonly studied topics in various domains of research. Hence, the community continuously produces multiple techniques, solutions, and tools to perform such tasks. However, running those tools and integrating them within existing infrastructure requires time, expertise, and resources. One pertinent task here is triples extraction and linking, where structured triples are extracted from a text and aligned to an existing Knowledge Graph (KG). In this paper, we present Plumber , the first framework that allows users to manually and automatically create suitable IE pipelines from a community-created pool of tools to perform triple extraction and alignment on unstructured text. Our approach provides an interactive medium to alter the pipelines and perform IE tasks. A short video to show the working of the framework for different use-cases is available online1.

KW - Information Extraction

KW - NLP Pipelines

KW - Semantic Web

KW - Software Reusability

UR - http://www.scopus.com/inward/record.url?scp=85107643199&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2206.01442

DO - 10.48550/arXiv.2206.01442

M3 - Conference contribution

AN - SCOPUS:85107643199

SP - 678

EP - 679

BT - The Web Conference 2021

Y2 - 19 April 2021 through 23 April 2021

ER -

By the same author(s)