Query-based single document summarization using an Ensemble Noisy Auto-Encoder

In this paper we use a deep auto-encoder for extractive query-based summarization. We experiment with different input representations in order to overcome the problems stemming from sparse inputs characteristic to linguistic data. In particular, we propose constructing a local vocabulary for each document and adding a small random noise to the input. Also, we propose using inputs with added noise in an Ensemble Noisy Auto-Encoder (ENAE) that combines the top ranked sentences from multiple runs on the same input with different added noise. We test our model on a publicly available email dataset that is specifi- cally designed for text summarization. We show that although an auto-encoder can be a quite effective summarizer, adding noise to the input and running a noisy ensemble can make improvements