Multilingual Fine-Grained Entity Typing

M.G.J. van Erp, P.T.J.M. Vossen

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Many entity recognition approaches classify recognised entities into a limited set of coarse-grained entity types. However, for deeper natural language analysis and end-user tasks, fine-grained entity types are more useful. For example, while standard named entity recognition may determine that an entity is a person knowing whether that entity is a politician or an actor is important for determining whether, in a subsequent relation extraction task, a relation should be acts or governs. Currently, fine-grained entity typing has only been investigated for English. In this paper, we present a fine-grained entity typing system for Dutch and Spanish using training data extracted from Wikipedia and DBpedia. Our system achieves comparable performance to English with an F1 measure of .90 on over 40 types for both Dutch and Spanish.
LanguageEnglish
Pages262-275
Number of pages14
JournalLecture Notes in Computer Science
VolumeLNAI
Issue number10318
DOIs
Publication statusPublished - 2017

Fingerprint

Named Entity Recognition
Wikipedia
Natural Language
Person
Classify
Training
Standards
Actors

Bibliographical note

Language, Data, and Knowledge: First International Conference, LDK 2017, Galway, Ireland, June 19-20, 2017, Proceedings

Lecture Notes in Artificial Intelligence 10318
Subseries of Lecture Notes in Computer Science

Cite this

van Erp, M.G.J. ; Vossen, P.T.J.M. / Multilingual Fine-Grained Entity Typing. In: Lecture Notes in Computer Science. 2017 ; Vol. LNAI, No. 10318. pp. 262-275.
@article{7fbd4be85dba4fafa9768b3a8f88e82d,
title = "Multilingual Fine-Grained Entity Typing",
abstract = "Many entity recognition approaches classify recognised entities into a limited set of coarse-grained entity types. However, for deeper natural language analysis and end-user tasks, fine-grained entity types are more useful. For example, while standard named entity recognition may determine that an entity is a person knowing whether that entity is a politician or an actor is important for determining whether, in a subsequent relation extraction task, a relation should be acts or governs. Currently, fine-grained entity typing has only been investigated for English. In this paper, we present a fine-grained entity typing system for Dutch and Spanish using training data extracted from Wikipedia and DBpedia. Our system achieves comparable performance to English with an F1 measure of .90 on over 40 types for both Dutch and Spanish.",
author = "{van Erp}, M.G.J. and P.T.J.M. Vossen",
note = "Language, Data, and Knowledge: First International Conference, LDK 2017, Galway, Ireland, June 19-20, 2017, Proceedings Lecture Notes in Artificial Intelligence 10318 Subseries of Lecture Notes in Computer Science",
year = "2017",
doi = "10.1007/978-3-319-59888-8_23",
language = "English",
volume = "LNAI",
pages = "262--275",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
number = "10318",

}

Multilingual Fine-Grained Entity Typing. / van Erp, M.G.J.; Vossen, P.T.J.M.

In: Lecture Notes in Computer Science, Vol. LNAI, No. 10318, 2017, p. 262-275.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Multilingual Fine-Grained Entity Typing

AU - van Erp, M.G.J.

AU - Vossen, P.T.J.M.

N1 - Language, Data, and Knowledge: First International Conference, LDK 2017, Galway, Ireland, June 19-20, 2017, Proceedings Lecture Notes in Artificial Intelligence 10318 Subseries of Lecture Notes in Computer Science

PY - 2017

Y1 - 2017

N2 - Many entity recognition approaches classify recognised entities into a limited set of coarse-grained entity types. However, for deeper natural language analysis and end-user tasks, fine-grained entity types are more useful. For example, while standard named entity recognition may determine that an entity is a person knowing whether that entity is a politician or an actor is important for determining whether, in a subsequent relation extraction task, a relation should be acts or governs. Currently, fine-grained entity typing has only been investigated for English. In this paper, we present a fine-grained entity typing system for Dutch and Spanish using training data extracted from Wikipedia and DBpedia. Our system achieves comparable performance to English with an F1 measure of .90 on over 40 types for both Dutch and Spanish.

AB - Many entity recognition approaches classify recognised entities into a limited set of coarse-grained entity types. However, for deeper natural language analysis and end-user tasks, fine-grained entity types are more useful. For example, while standard named entity recognition may determine that an entity is a person knowing whether that entity is a politician or an actor is important for determining whether, in a subsequent relation extraction task, a relation should be acts or governs. Currently, fine-grained entity typing has only been investigated for English. In this paper, we present a fine-grained entity typing system for Dutch and Spanish using training data extracted from Wikipedia and DBpedia. Our system achieves comparable performance to English with an F1 measure of .90 on over 40 types for both Dutch and Spanish.

U2 - 10.1007/978-3-319-59888-8_23

DO - 10.1007/978-3-319-59888-8_23

M3 - Article

VL - LNAI

SP - 262

EP - 275

JO - Lecture Notes in Computer Science

T2 - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - 10318

ER -