Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
arXiv:1809.06590
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 mean-max 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 high-quality 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 and the advanced skip-thoughts+LN model. Furthermore, compared with the traditional recurrent neural network, our mean-max AAE greatly reduce the training time.
arXiv commentEMNLP 2018
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Efficient Estimation of Word Representations in Vector Space
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Universal Sentence Encoder
- Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
- A large annotated corpus for learning natural language inference
- An efficient framework for learning sentence representations
- Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning