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 language | English |
---|---|
Title of host publication | Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media |
Place of Publication | Valencia |
Publisher | Association for Computational Linguistics |
Pages | 36-44 |
Publication status | Published - Apr 2017 |
Event | European Chapter of the Association for Computational Linguistics: SocialNLP Workshop - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 https://sites.google.com/site/socialnlp2017/ |
Conference
Conference | European Chapter of the Association for Computational Linguistics |
---|---|
Abbreviated title | EACL2017 |
Country/Territory | Spain |
City | Valencia |
Period | 03/04/2017 → 07/04/2017 |
Internet address |