Character-based Neural Embeddings for Tweet Clustering

Svitlana Vakulenko, Lyndon Nixon, Mahai Lupu

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

Abstract

In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. Theproposedapproachovercomes the limitations related to the vocabulary explosion in the word-based models and allows for the seamless processing of the multilingual content. Our evaluation results and code are available on-line.
Original languageEnglish
Title of host publicationProceedings of the Fifth International Workshop on Natural Language Processing for Social Media
Place of PublicationValencia
PublisherAssociation for Computational Linguistics
Pages36-44
Publication statusPublished - Apr 2017
EventEuropean Chapter of the Association for Computational Linguistics: SocialNLP Workshop - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017
https://sites.google.com/site/socialnlp2017/

Conference

ConferenceEuropean Chapter of the Association for Computational Linguistics
Abbreviated titleEACL2017
Country/TerritorySpain
CityValencia
Period03/04/201707/04/2017
Internet address

Fingerprint

Dive into the research topics of 'Character-based Neural Embeddings for Tweet Clustering'. Together they form a unique fingerprint.

Cite this