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

Mahmood Yousefi Azar, Kairit Sirts, Diego Molla Aliod, Len Hamey

Research output: Contribution to journalConference paper

Abstract

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
Original languageEnglish
Pages (from-to)2-10
Number of pages9
JournalALTA 2015 : Proceedings of Australasian Language Technology Association Workshop 2015
Publication statusPublished - 2015
EventAustralasian Language Technology Association Workshop (13th : 2015) - Parramatta, NSW
Duration: 8 Dec 20159 Dec 2015

Fingerprint Dive into the research topics of 'Query-based single document summarization using an Ensemble Noisy Auto-Encoder'. Together they form a unique fingerprint.

Cite this