Learning Generic Sentence Representations Using Convolutional Neural Networks
This work addresses the need for versatile sentence embeddings in natural language processing, though it appears incremental as it builds on existing encoder-decoder and neural network techniques.
The authors tackled the problem of learning generic sentence representations by proposing an encoder-decoder model using a CNN encoder and LSTM decoder, trained on novels, which achieved superior performance across multiple benchmark datasets and applications.
We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a continuous vector, and using a long short-term memory recurrent neural network as a decoder. Several tasks are considered, including sentence reconstruction and future sentence prediction. Further, a hierarchical encoder-decoder model is proposed to encode a sentence to predict multiple future sentences. By training our models on a large collection of novels, we obtain a highly generic convolutional sentence encoder that performs well in practice. Experimental results on several benchmark datasets, and across a broad range of applications, demonstrate the superiority of the proposed model over competing methods.