@inproceedings{72f28baf5527435f9dc562a7c18c10ee,
title = "Regularizing Deep Text Models by Encouraging Competition",
abstract = "The difficulty in acquiring a large amount of labelled training data and the demand of complex neural network models in text learning make developing effective regularization techniques an important research topic. In this paper, we present a novel regularization scheme for supervised text learning, Competitive Word Dropout, or CWD. Experiments on three different natural language learning tasks demonstrate that CWD outperforms significantly the standard regularization schemes such as weight decay and dropout. The CWD scheme has another unique advantage, namely that it can be interpreted semantically.",
keywords = "Deep learning, Regularization, Text learning, Word dropout, Word embedding",
author = "Jiaran Li and Richong Zhang and Yuan Tian",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 7th China Conference on Knowledge Graph and Semantic Computing, CCKS 2022 ; Conference date: 24-08-2022 Through 27-08-2022",
year = "2022",
doi = "10.1007/978-981-19-7596-7\_13",
language = "英语",
isbn = "9789811975950",
series = "Communications in Computer and Information Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "161--173",
editor = "Maosong Sun and Bin Xu and Guilin Qi and Kang Liu and Yubo Chen and Jiadong Ren and Yansong Feng and Yongbin Liu",
booktitle = "Knowledge Graph and Semantic Computing",
address = "德国",
}