@inproceedings{zhou-etal-2017-event,
title = "Event extraction from {T}witter using Non-Parametric {B}ayesian Mixture Model with Word Embeddings",
author = "Zhou, Deyu and
Zhang, Xuan and
He, Yulan",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1076",
pages = "808--817",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2017-event">
<titleInfo>
<title>Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zhou-etal-2017-event</identifier>
<location>
<url>https://aclanthology.org/E17-1076</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>808</start>
<end>817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings
%A Zhou, Deyu
%A Zhang, Xuan
%A He, Yulan
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F zhou-etal-2017-event
%X 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.
%U https://aclanthology.org/E17-1076
%P 808-817
Markdown (Informal)
[Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings](https://aclanthology.org/E17-1076) (Zhou et al., EACL 2017)
ACL