Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings

Deyu Zhou, Xuan Zhang, Yulan He

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

Abstract

To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event. Hence, they group tweets into clusters based on the co-occurrence patterns of named entities and topical keywords. However, there are two main limitations. First, they require the number of events to be known beforehand, which is not realistic in practical applications. Second, they don’t recognise that the same named entity might be referred to by multiple mentions and tweets using different mentions would be wrongly assigned to different events. To overcome these limitations, we propose a non-parametric Bayesian mixture model with word embeddings for event extraction, in which the number of events can be inferred automatically and the issue of lexical variations for the same named entity can be dealt with properly. Our model has been evaluated on three datasets with sizes ranging between 2,499 and over 60 million tweets. Experimental results show that our model outperforms the baseline approach on all datasets by 5-8% in F-measure.
Original languageEnglish
Title of host publicationProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
Pages808–817
Number of pages10
Volume1
ISBN (Electronic)978-1-51083860-4
Publication statusPublished - 7 Apr 2017
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia Conference Center, Valencia, Spain
Duration: 3 Apr 20177 Apr 2017

Conference

Conference15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
CountrySpain
CityValencia
Period3/04/177/04/17

Fingerprint

twitter
event
Mixture Model
Entity
Group

Bibliographical note

-

Cite this

Zhou, D., Zhang, X., & He, Y. (2017). Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (Vol. 1, pp. 808–817). Association for Computational Linguistics.
Zhou, Deyu ; Zhang, Xuan ; He, Yulan. / Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Vol. 1 Association for Computational Linguistics, 2017. pp. 808–817
@inproceedings{82cdf3ae68c14afe801e21ba89dc4da6,
title = "Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings",
abstract = "To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event. Hence, they group tweets into clusters based on the co-occurrence patterns of named entities and topical keywords. However, there are two main limitations. First, they require the number of events to be known beforehand, which is not realistic in practical applications. Second, they don’t recognise that the same named entity might be referred to by multiple mentions and tweets using different mentions would be wrongly assigned to different events. To overcome these limitations, we propose a non-parametric Bayesian mixture model with word embeddings for event extraction, in which the number of events can be inferred automatically and the issue of lexical variations for the same named entity can be dealt with properly. Our model has been evaluated on three datasets with sizes ranging between 2,499 and over 60 million tweets. Experimental results show that our model outperforms the baseline approach on all datasets by 5-8{\%} in F-measure.",
author = "Deyu Zhou and Xuan Zhang and Yulan He",
note = "-",
year = "2017",
month = "4",
day = "7",
language = "English",
volume = "1",
pages = "808–817",
booktitle = "Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics",

}

Zhou, D, Zhang, X & He, Y 2017, Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings. in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. vol. 1, Association for Computational Linguistics, pp. 808–817, 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, 3/04/17.

Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings. / Zhou, Deyu; Zhang, Xuan; He, Yulan.

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Vol. 1 Association for Computational Linguistics, 2017. p. 808–817.

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

TY - GEN

T1 - Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings

AU - Zhou, Deyu

AU - Zhang, Xuan

AU - He, Yulan

N1 - -

PY - 2017/4/7

Y1 - 2017/4/7

N2 - To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event. Hence, they group tweets into clusters based on the co-occurrence patterns of named entities and topical keywords. However, there are two main limitations. First, they require the number of events to be known beforehand, which is not realistic in practical applications. Second, they don’t recognise that the same named entity might be referred to by multiple mentions and tweets using different mentions would be wrongly assigned to different events. To overcome these limitations, we propose a non-parametric Bayesian mixture model with word embeddings for event extraction, in which the number of events can be inferred automatically and the issue of lexical variations for the same named entity can be dealt with properly. Our model has been evaluated on three datasets with sizes ranging between 2,499 and over 60 million tweets. Experimental results show that our model outperforms the baseline approach on all datasets by 5-8% in F-measure.

AB - To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event. Hence, they group tweets into clusters based on the co-occurrence patterns of named entities and topical keywords. However, there are two main limitations. First, they require the number of events to be known beforehand, which is not realistic in practical applications. Second, they don’t recognise that the same named entity might be referred to by multiple mentions and tweets using different mentions would be wrongly assigned to different events. To overcome these limitations, we propose a non-parametric Bayesian mixture model with word embeddings for event extraction, in which the number of events can be inferred automatically and the issue of lexical variations for the same named entity can be dealt with properly. Our model has been evaluated on three datasets with sizes ranging between 2,499 and over 60 million tweets. Experimental results show that our model outperforms the baseline approach on all datasets by 5-8% in F-measure.

UR - http://www.scopus.com/inward/record.url?scp=85021649806&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85021649806

VL - 1

SP - 808

EP - 817

BT - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics

ER -

Zhou D, Zhang X, He Y. Event extraction from Twitter using non-parametric Bayesian mixture model with word embeddings. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Vol. 1. Association for Computational Linguistics. 2017. p. 808–817