Character-based Neural Embeddings for Tweet Clustering
Information Retrieval
2017-03-17 v2 Computation and Language
Abstract
In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes 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 at https://github.com/vendi12/tweet2vec_clustering
Cite
@article{arxiv.1703.05123,
title = {Character-based Neural Embeddings for Tweet Clustering},
author = {Svitlana Vakulenko and Lyndon Nixon and Mihai Lupu},
journal= {arXiv preprint arXiv:1703.05123},
year = {2017}
}
Comments
Accepted at the SocialNLP 2017 workshop held in conjunction with EACL 2017, April 3, 2017, Valencia, Spain