Learning Universal Sentence Representations with Mean-Max Attention Autoencoder

Abstract

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a meanmax attention autoencoder (mean-max AAE) within the encoder-decoder framework. Our autoencoder rely entirely on the MultiHead self-attention mechanism to reconstruct the input sequence. In the encoding we propose a mean-max strategy that applies both mean and max pooling operations over the hidden vectors to capture diverse information of the input. To enable the information to steer the reconstruction process dynamically, the decoder performs attention over the mean-max representation. By training our model on a large collection of unlabelled data, we obtain highquality representations of sentences. Experimental results on a broad range of 10 transfer tasks demonstrate that our model outperforms the state-of-the-art unsupervised single methods, including the classical skip-thoughts Furthermore, compared with the traditional recurrent neural network, our mean-max AAE greatly reduce the training time.