A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data

Ilkcan Keles, Omar Qawasmeh, Tabea Tietz, Ludovica Marinucci, Roberto Reda, Marieke Van Erp

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Resumé

The Web of Data has grown explosively over the past few years, and as with any dataset, there are bound to be invalid statements in the data, as well as gaps. Natural Language Processing (NLP) is gaining interest to fill gaps in data by transforming (unstructured) text into structured data. However, there is currently a fundamental mismatch in approaches between Linked Data and NLP as the latter is often based on statistical methods, and the former on explicitly modelling knowledge. However, these fields can strengthen each other by joining forces. In this position paper, we argue that using linked data to validate the output of an NLP system, and using textual data to validate Linked Open Data (LOD) cloud statements is a promising research avenue. We illustrate our proposal with a proof of concept on a corpus of historical travel stories.
OriginalsprogEngelsk
Titel2nd Conference on Language, Data and Knowledge (LDK 2019)
Antal sider8
Vol/bind70
ForlagSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
Publikationsdato2019
Sider13:1-13:8
ISBN (Trykt)978-3-95977-105-4
DOI
StatusUdgivet - 2019
BegivenhedConference on Language, Data and Knowledge - Leipzig, Tyskland
Varighed: 20 maj 201923 maj 2019
Konferencens nummer: 2nd
http://2019.ldk-conf.org/

Konference

KonferenceConference on Language, Data and Knowledge
Nummer2nd
LandTyskland
ByLeipzig
Periode20/05/201923/05/2019
Internetadresse

Fingerprint

Natural language processing systems
Processing
Joining
Statistical methods

Citer dette

Keles, I., Qawasmeh, O., Tietz, T., Marinucci, L., Reda, R., & Van Erp, M. (2019). A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data. I 2nd Conference on Language, Data and Knowledge (LDK 2019) (Bind 70, s. 13:1-13:8). Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. https://doi.org/10.4230/OASIcs.LDK.2019.13
Keles, Ilkcan ; Qawasmeh, Omar ; Tietz, Tabea ; Marinucci, Ludovica ; Reda, Roberto ; Van Erp, Marieke. / A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data. 2nd Conference on Language, Data and Knowledge (LDK 2019). Bind 70 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing, 2019. s. 13:1-13:8
@inproceedings{f5d82e3279c44323909020a4d20fc94d,
title = "A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data",
abstract = "The Web of Data has grown explosively over the past few years, and as with any dataset, there are bound to be invalid statements in the data, as well as gaps. Natural Language Processing (NLP) is gaining interest to fill gaps in data by transforming (unstructured) text into structured data. However, there is currently a fundamental mismatch in approaches between Linked Data and NLP as the latter is often based on statistical methods, and the former on explicitly modelling knowledge. However, these fields can strengthen each other by joining forces. In this position paper, we argue that using linked data to validate the output of an NLP system, and using textual data to validate Linked Open Data (LOD) cloud statements is a promising research avenue. We illustrate our proposal with a proof of concept on a corpus of historical travel stories.",
author = "Ilkcan Keles and Omar Qawasmeh and Tabea Tietz and Ludovica Marinucci and Roberto Reda and {Van Erp}, Marieke",
year = "2019",
doi = "10.4230/OASIcs.LDK.2019.13",
language = "English",
isbn = "978-3-95977-105-4",
volume = "70",
pages = "13:1--13:8",
booktitle = "2nd Conference on Language, Data and Knowledge (LDK 2019)",
publisher = "Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing",

}

Keles, I, Qawasmeh, O, Tietz, T, Marinucci, L, Reda, R & Van Erp, M 2019, A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data. i 2nd Conference on Language, Data and Knowledge (LDK 2019). bind 70, Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing, s. 13:1-13:8, Leipzig, Tyskland, 20/05/2019. https://doi.org/10.4230/OASIcs.LDK.2019.13

A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data. / Keles, Ilkcan; Qawasmeh, Omar; Tietz, Tabea; Marinucci, Ludovica; Reda, Roberto; Van Erp, Marieke.

2nd Conference on Language, Data and Knowledge (LDK 2019). Bind 70 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing, 2019. s. 13:1-13:8.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data

AU - Keles, Ilkcan

AU - Qawasmeh, Omar

AU - Tietz, Tabea

AU - Marinucci, Ludovica

AU - Reda, Roberto

AU - Van Erp, Marieke

PY - 2019

Y1 - 2019

N2 - The Web of Data has grown explosively over the past few years, and as with any dataset, there are bound to be invalid statements in the data, as well as gaps. Natural Language Processing (NLP) is gaining interest to fill gaps in data by transforming (unstructured) text into structured data. However, there is currently a fundamental mismatch in approaches between Linked Data and NLP as the latter is often based on statistical methods, and the former on explicitly modelling knowledge. However, these fields can strengthen each other by joining forces. In this position paper, we argue that using linked data to validate the output of an NLP system, and using textual data to validate Linked Open Data (LOD) cloud statements is a promising research avenue. We illustrate our proposal with a proof of concept on a corpus of historical travel stories.

AB - The Web of Data has grown explosively over the past few years, and as with any dataset, there are bound to be invalid statements in the data, as well as gaps. Natural Language Processing (NLP) is gaining interest to fill gaps in data by transforming (unstructured) text into structured data. However, there is currently a fundamental mismatch in approaches between Linked Data and NLP as the latter is often based on statistical methods, and the former on explicitly modelling knowledge. However, these fields can strengthen each other by joining forces. In this position paper, we argue that using linked data to validate the output of an NLP system, and using textual data to validate Linked Open Data (LOD) cloud statements is a promising research avenue. We illustrate our proposal with a proof of concept on a corpus of historical travel stories.

U2 - 10.4230/OASIcs.LDK.2019.13

DO - 10.4230/OASIcs.LDK.2019.13

M3 - Article in proceeding

SN - 978-3-95977-105-4

VL - 70

SP - 13:1-13:8

BT - 2nd Conference on Language, Data and Knowledge (LDK 2019)

PB - Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing

ER -

Keles I, Qawasmeh O, Tietz T, Marinucci L, Reda R, Van Erp M. A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data. I 2nd Conference on Language, Data and Knowledge (LDK 2019). Bind 70. Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. 2019. s. 13:1-13:8 https://doi.org/10.4230/OASIcs.LDK.2019.13