Initializing Convolutional Filters with Semantic Features for Text Classification

Shen Li, Zhe Zhao, Tao Liu, Renfen Hu, Xiaoyong Du


Abstract
Convolutional Neural Networks (CNNs) are widely used in NLP tasks. This paper presents a novel weight initialization method to improve the CNNs for text classification. Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training. Experiments demonstrate the effectiveness of the initialization technique on seven text classification tasks, including sentiment analysis and topic classification.
Anthology ID:
D17-1201
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1884–1889
Language:
URL:
https://aclanthology.org/D17-1201
DOI:
10.18653/v1/D17-1201
Bibkey:
Cite (ACL):
Shen Li, Zhe Zhao, Tao Liu, Renfen Hu, and Xiaoyong Du. 2017. Initializing Convolutional Filters with Semantic Features for Text Classification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1884–1889, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Initializing Convolutional Filters with Semantic Features for Text Classification (Li et al., EMNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/D17-1201.pdf
Attachment:
 D17-1201.Attachment.pdf
Data
MPQA Opinion CorpusSST