期刊
NEUROCOMPUTING
卷 378, 期 -, 页码 315-323出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.08.096
关键词
Natural language processing; Convolutional neural networks; Padding
资金
- Universitat Politecnica de Valencia [PAID-01-2461 2015]
- GVA [PROMETEO/2018/002]
- NVIDIA Corporation
In this work, a methodology for applying semantic-based padding in Convolutional Neural Networks for Natural Language Processing tasks is proposed. Semantic-based padding takes advantage of the unused space required for having a fixed-size input matrix in a Convolutional Network effectively, using words present in the sentence. The methodology proposed has been evaluated intensively in Sentiment Analysis tasks using a variety of word embeddings. In all the experimentation carried out the proposed semantic-based padding improved the results achieved when no padding strategy is applied. Moreover, when the model used a pre-trained word embeddings, the performance of the state of the art has been surpassed. (C) 2019 Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据