中文

深度学习与词嵌入用于危机响应中的推文分类

计算与语言 2019-03-27 v1 机器学习

摘要

传统的危机响应推文分类模型侧重于卷积层与领域特定词嵌入。本文中,我们研究不同神经网络结合通用与领域特定词嵌入的应用,以考察它们提升推文分类模型性能的能力。我们在CrisisNLP数据集上评估了四种推文分类模型,获得了可比的结果,这表明通用词嵌入(如GloVe)可替代领域特定词嵌入,尤其是在Bi-LSTM中,其报告的最高F1分数为62.04%。

关键词

引用

@article{arxiv.1903.11024,
  title  = {Deep Learning and Word Embeddings for Tweet Classification for Crisis Response},
  author = {Reem ALRashdi and Simon O'Keefe},
  journal= {arXiv preprint arXiv:1903.11024},
  year   = {2019}
}

备注

This paper has been accepted and presented in the 3rd National Computing Colleges Conference (NC3) in Abha, Saudi Arabia on 9th October 2018