Compositional Coding Capsule Network with K-Means Routing for Text Classification

22 Oct 2018  ·  Hao Ren, Hong Lu ·

Text classification is a challenging problem which aims to identify the category of texts. In the process of training, word embeddings occupy a large part of parameters. Under the limitation of limited computing resources, it indirectly limits the ability of subsequent network designs. In order to reduce the number of parameters, the compositional coding mechanism has been proposed recently. Based on this, this paper further explores compositional coding and proposes a compositional weighted coding method. And we apply capsule network to model the relationship between word embeddings, a new routing algorithm, which is based on k-means clustering theory, is proposed to fully mine the relationship between word embeddings. Combined with our compositional weighted coding method and the routing algorithm, we design a neural network for text classification. Experiments conducted on eight challenging text classification datasets show that the proposed method achieves competitive accuracy compared to the state-of-the-art approach with significantly fewer parameters.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Classification AG News CCCapsNet Error 7.61 # 15
Sentiment Analysis Amazon Review Full CCCapsNet Accuracy 60.95 # 7
Sentiment Analysis Amazon Review Polarity CCCapsNet Accuracy 94.96 # 7
Text Classification DBpedia CCCapsNet Error 1.28 # 16
Text Classification Sogou News CCCapsNet Accuracy 97.25 # 2
Text Classification Yahoo! Answers CCCapsNet Accuracy 73.85 # 7
Sentiment Analysis Yelp Binary classification CCCapsNet Error 3.52 # 12
Sentiment Analysis Yelp Fine-grained classification CCCapsNet Error 34.15 # 11

Methods