@inproceedings{saravanakumar-etal-2021-event,
title = "Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings",
author = "Saravanakumar, Kailash Karthik and
Ballesteros, Miguel and
Chandrasekaran, Muthu Kumar and
McKeown, Kathleen",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.198",
doi = "10.18653/v1/2021.eacl-main.198",
pages = "2330--2340",
abstract = "We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document representations, aggregates document-cluster similarity along these multiple representations and makes the clustering decision using a neural classifier. The weighted document-cluster similarity model is learned using a novel adaptation of the triplet loss into a linear classification objective. We show that the use of a suitable fine-tuning objective and external knowledge in pre-trained transformer models yields significant improvements in the effectiveness of contextual embeddings for clustering. Our model achieves a new state-of-the-art on a standard stream clustering dataset of English documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saravanakumar-etal-2021-event">
<titleInfo>
<title>Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kailash</namePart>
<namePart type="given">Karthik</namePart>
<namePart type="family">Saravanakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muthu</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Chandrasekaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document representations, aggregates document-cluster similarity along these multiple representations and makes the clustering decision using a neural classifier. The weighted document-cluster similarity model is learned using a novel adaptation of the triplet loss into a linear classification objective. We show that the use of a suitable fine-tuning objective and external knowledge in pre-trained transformer models yields significant improvements in the effectiveness of contextual embeddings for clustering. Our model achieves a new state-of-the-art on a standard stream clustering dataset of English documents.</abstract>
<identifier type="citekey">saravanakumar-etal-2021-event</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.198</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.198</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>2330</start>
<end>2340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
%A Saravanakumar, Kailash Karthik
%A Ballesteros, Miguel
%A Chandrasekaran, Muthu Kumar
%A McKeown, Kathleen
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F saravanakumar-etal-2021-event
%X We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document representations, aggregates document-cluster similarity along these multiple representations and makes the clustering decision using a neural classifier. The weighted document-cluster similarity model is learned using a novel adaptation of the triplet loss into a linear classification objective. We show that the use of a suitable fine-tuning objective and external knowledge in pre-trained transformer models yields significant improvements in the effectiveness of contextual embeddings for clustering. Our model achieves a new state-of-the-art on a standard stream clustering dataset of English documents.
%R 10.18653/v1/2021.eacl-main.198
%U https://aclanthology.org/2021.eacl-main.198
%U https://doi.org/10.18653/v1/2021.eacl-main.198
%P 2330-2340
Markdown (Informal)
[Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings](https://aclanthology.org/2021.eacl-main.198) (Saravanakumar et al., EACL 2021)
ACL