Resilient Combination of Complementary CNN and RNN Features for Text Classification through Attention and Ensembling
This work addresses text classification for applications needing robust models, but it is incremental as it builds on existing neural modules.
The paper tackled text classification by combining convolution, recurrent, and attention neural modules with ensemble methods, showing they are complementary and introducing ECGA, an end-to-end architecture that attains or surpasses state-of-the-art performance on varied datasets.
State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing. In this work, we focus on end-to-end neural architectures and show that the best performance in text classification is obtained by combining information from different neural modules. Concretely, we combine convolution, recurrent and attention modules with ensemble methods and show that they are complementary. We introduce ECGA, an end-to-end go-to architecture for novel text classification tasks. We prove that it is efficient and robust, as it attains or surpasses the state-of-the-art on varied datasets, including both low and high data regimes.