Good Applications for Crummy Entity Linkers?: The Case of Corpus Selection in Digital Humanities

Alex  Olieman; Kaspar Beelen; Milan Lange, van; Jaap  Kamps; Maarten Marx

Good Applications for Crummy Entity Linkers? The Case of Corpus Selection in Digital Humanities

Alex Olieman, Kaspar Beelen, Milan Lange, van, Jaap Kamps, Maarten Marx

NIOD Institute for War, Holocaust and Genocide studies

Research output: Contribution to conference › Paper › Scientific › peer-review

Abstract

Over the last decade we have made great progress in entity linking (EL) systems, but performance may vary depending on the context and, arguably, there are even principled limitations prevent a "perfect" EL system. This also suggests that there may be applications for which current "imperfect" EL is already very useful, and makes finding the "right" application as important as building the "right" EL system.

We investigate the Digital Humanities use case, where scholars spend a considerable amount of time selecting relevant source texts. We developed WideNet; a semantically-enhanced search tool which leverages the strengths of (imperfect) EL without getting in the way of its expert users. We evaluate this tool in two historical case-studies aiming to collect a set of references to historical periods in parliamentary debates from the last two decades; the first targeted the Dutch Golden Age, and the second World War II.

The case-studies conclude with a critical reflection on the utility of WideNet for this kind of research, after which we outline how such a real-world application can help to improve EL technology in general.

Original language	English
Number of pages	8
Publication status	Published - 2017
Event	SEMANTiCS 2017 - De Meervaart, Amsterdam, Netherlands Duration: 11 Sept 2017 → 14 Sept 2017 https://2017.semantics.cc/

Conference

Conference	SEMANTiCS 2017
Country/Territory	Netherlands
City	Amsterdam
Period	11/09/2017 → 14/09/2017
Other	SEMANTiCS 2017 is an international event on Linked Data and the Semantic Web where business users, vendors and academia meet. Widely recognized to be of pivotal importance, it is the thirteenth edition of a well-attended yearly conference that started back in 2005. It offers keynotes by world-class practitioners, presentations and field reports in diverse tracks, talks addressing a variety of topics, and panel discussions. And, of course, ample opportunities for networking and meeting like-minded professionals in an informal setting.
Internet address	https://2017.semantics.cc/

Keywords

entity linking
digital humanities
corpus selection

Access to Document

https://arxiv.org/pdf/1708.01162.pdfLicence: CC BY-NC

1 PhD thesis

Emotional Imprints: A Computer-assisted Analysis of War-related Emotions in Dutch Parliamentary Debates, 1945–1989
Lange, van, M., 10 Dec 2021, Utrecht: Utrecht University. 261 p.
Research output: PhD Thesis › PhD thesis

Open Access

Cite this

@conference{479ce3b5b2574ba9ac97457046ca364e,

title = "Good Applications for Crummy Entity Linkers?: The Case of Corpus Selection in Digital Humanities",

abstract = "Over the last decade we have made great progress in entity linking (EL) systems, but performance may vary depending on the context and, arguably, there are even principled limitations prevent a {"}perfect{"} EL system. This also suggests that there may be applications for which current {"}imperfect{"} EL is already very useful, and makes finding the {"}right{"} application as important as building the {"}right{"} EL system.We investigate the Digital Humanities use case, where scholars spend a considerable amount of time selecting relevant source texts. We developed WideNet; a semantically-enhanced search tool which leverages the strengths of (imperfect) EL without getting in the way of its expert users. We evaluate this tool in two historical case-studies aiming to collect a set of references to historical periods in parliamentary debates from the last two decades; the first targeted the Dutch Golden Age, and the second World War II.The case-studies conclude with a critical reflection on the utility of WideNet for this kind of research, after which we outline how such a real-world application can help to improve EL technology in general.",

keywords = "entity linking, digital humanities, corpus selection",

author = "Alex Olieman and Kaspar Beelen and {Lange, van}, Milan and Jaap Kamps and Maarten Marx",

year = "2017",

language = "English",

note = "SEMANTiCS 2017 ; Conference date: 11-09-2017 Through 14-09-2017",

url = "https://2017.semantics.cc/",

}

TY - CONF

T1 - Good Applications for Crummy Entity Linkers?

T2 - SEMANTiCS 2017

AU - Olieman, Alex

AU - Beelen, Kaspar

AU - Lange, van, Milan

AU - Kamps, Jaap

AU - Marx, Maarten

PY - 2017

Y1 - 2017

N2 - Over the last decade we have made great progress in entity linking (EL) systems, but performance may vary depending on the context and, arguably, there are even principled limitations prevent a "perfect" EL system. This also suggests that there may be applications for which current "imperfect" EL is already very useful, and makes finding the "right" application as important as building the "right" EL system.We investigate the Digital Humanities use case, where scholars spend a considerable amount of time selecting relevant source texts. We developed WideNet; a semantically-enhanced search tool which leverages the strengths of (imperfect) EL without getting in the way of its expert users. We evaluate this tool in two historical case-studies aiming to collect a set of references to historical periods in parliamentary debates from the last two decades; the first targeted the Dutch Golden Age, and the second World War II.The case-studies conclude with a critical reflection on the utility of WideNet for this kind of research, after which we outline how such a real-world application can help to improve EL technology in general.

AB - Over the last decade we have made great progress in entity linking (EL) systems, but performance may vary depending on the context and, arguably, there are even principled limitations prevent a "perfect" EL system. This also suggests that there may be applications for which current "imperfect" EL is already very useful, and makes finding the "right" application as important as building the "right" EL system.We investigate the Digital Humanities use case, where scholars spend a considerable amount of time selecting relevant source texts. We developed WideNet; a semantically-enhanced search tool which leverages the strengths of (imperfect) EL without getting in the way of its expert users. We evaluate this tool in two historical case-studies aiming to collect a set of references to historical periods in parliamentary debates from the last two decades; the first targeted the Dutch Golden Age, and the second World War II.The case-studies conclude with a critical reflection on the utility of WideNet for this kind of research, after which we outline how such a real-world application can help to improve EL technology in general.

KW - entity linking

KW - digital humanities

KW - corpus selection

M3 - Paper

Y2 - 11 September 2017 through 14 September 2017

ER -

Good Applications for Crummy Entity Linkers? The Case of Corpus Selection in Digital Humanities

Abstract

Conference

Keywords

Access to Document

Fingerprint

Research output

Emotional Imprints: A Computer-assisted Analysis of War-related Emotions in Dutch Parliamentary Debates, 1945–1989

Cite this