Character-level Convolutional Networks for Text Classification

NeurIPS 2015  ·  Xiang Zhang, Junbo Zhao, Yann Lecun ·

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.

PDF Abstract NeurIPS 2015 PDF NeurIPS 2015 Abstract

Datasets

Introduced in the Paper:

AG News Yahoo! Answers Yelp Review Polarity

Used in the Paper:

DBpedia Yelp
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Classification AG News Char-level CNN Error 9.51 # 19
Compare
Text Classification DBpedia Char-level CNN Error 1.55 # 20
Compare
Sentiment Analysis Yelp Binary classification Char-level CNN Error 4.88 # 20
Compare
Sentiment Analysis Yelp Fine-grained classification Char-level CNN Error 37.95 # 16
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy