Exploring multiple feature spaces for novel entity discovery

Zhaohui Wu, Yang Song, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Continuously discovering novel entities in news and Web data is important for Knowledge Base (KB) maintenance. One of the key challenges is to decide whether an entity mention refers to an in-KB or out-of-KB entity. We propose a principled approach that learns a novel entity classifier by modeling mention and entity representation into multiple feature spaces, including contextual, topical, lexical, neural embedding and query spaces. Different from most previous studies that address novel entity discovery as a submodule of entity linking systems, our model is more a generalized approach and can be applied as a pre-filtering step of novel entities for any entity linking systems. Experiments on three real-world datasets show that our method significantly outperforms existing methods on identifying novel entities.

Original languageEnglish (US)
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages3073-3079
Number of pages7
ISBN (Electronic)9781577357605
StatePublished - Jan 1 2016
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: Feb 12 2016Feb 17 2016

Publication series

Name30th AAAI Conference on Artificial Intelligence, AAAI 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period2/12/162/17/16

Fingerprint

Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Wu, Z., Song, Y., & Giles, C. L. (2016). Exploring multiple feature spaces for novel entity discovery. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 3073-3079). (30th AAAI Conference on Artificial Intelligence, AAAI 2016). AAAI press.
Wu, Zhaohui ; Song, Yang ; Giles, C. Lee. / Exploring multiple feature spaces for novel entity discovery. 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. pp. 3073-3079 (30th AAAI Conference on Artificial Intelligence, AAAI 2016).
@inproceedings{a97d837b9d56471a98864d9e94b5bddd,
title = "Exploring multiple feature spaces for novel entity discovery",
abstract = "Continuously discovering novel entities in news and Web data is important for Knowledge Base (KB) maintenance. One of the key challenges is to decide whether an entity mention refers to an in-KB or out-of-KB entity. We propose a principled approach that learns a novel entity classifier by modeling mention and entity representation into multiple feature spaces, including contextual, topical, lexical, neural embedding and query spaces. Different from most previous studies that address novel entity discovery as a submodule of entity linking systems, our model is more a generalized approach and can be applied as a pre-filtering step of novel entities for any entity linking systems. Experiments on three real-world datasets show that our method significantly outperforms existing methods on identifying novel entities.",
author = "Zhaohui Wu and Yang Song and Giles, {C. Lee}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
series = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",
publisher = "AAAI press",
pages = "3073--3079",
booktitle = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",

}

Wu, Z, Song, Y & Giles, CL 2016, Exploring multiple feature spaces for novel entity discovery. in 30th AAAI Conference on Artificial Intelligence, AAAI 2016. 30th AAAI Conference on Artificial Intelligence, AAAI 2016, AAAI press, pp. 3073-3079, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 2/12/16.

Exploring multiple feature spaces for novel entity discovery. / Wu, Zhaohui; Song, Yang; Giles, C. Lee.

30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 3073-3079 (30th AAAI Conference on Artificial Intelligence, AAAI 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring multiple feature spaces for novel entity discovery

AU - Wu, Zhaohui

AU - Song, Yang

AU - Giles, C. Lee

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Continuously discovering novel entities in news and Web data is important for Knowledge Base (KB) maintenance. One of the key challenges is to decide whether an entity mention refers to an in-KB or out-of-KB entity. We propose a principled approach that learns a novel entity classifier by modeling mention and entity representation into multiple feature spaces, including contextual, topical, lexical, neural embedding and query spaces. Different from most previous studies that address novel entity discovery as a submodule of entity linking systems, our model is more a generalized approach and can be applied as a pre-filtering step of novel entities for any entity linking systems. Experiments on three real-world datasets show that our method significantly outperforms existing methods on identifying novel entities.

AB - Continuously discovering novel entities in news and Web data is important for Knowledge Base (KB) maintenance. One of the key challenges is to decide whether an entity mention refers to an in-KB or out-of-KB entity. We propose a principled approach that learns a novel entity classifier by modeling mention and entity representation into multiple feature spaces, including contextual, topical, lexical, neural embedding and query spaces. Different from most previous studies that address novel entity discovery as a submodule of entity linking systems, our model is more a generalized approach and can be applied as a pre-filtering step of novel entities for any entity linking systems. Experiments on three real-world datasets show that our method significantly outperforms existing methods on identifying novel entities.

UR - http://www.scopus.com/inward/record.url?scp=84997564622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997564622&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84997564622

T3 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

SP - 3073

EP - 3079

BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

PB - AAAI press

ER -

Wu Z, Song Y, Giles CL. Exploring multiple feature spaces for novel entity discovery. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press. 2016. p. 3073-3079. (30th AAAI Conference on Artificial Intelligence, AAAI 2016).