Salience Estimation via Variational Auto-Encoders for Multi-Document Summarization
Refereed conference paper presented and published in conference proceedings

摘要We propose a new unsupervised sentence salience framework for Multi-Document Summarization (MDS), which can be divided into two components: latent semantic modeling and salience estimation. For latent semantic modeling, a neural generative model called Variational Auto-Encoders (VAEs) is employed to describe the observed sentences and the corresponding latent semantic representations. Neural variational inference is used for the posterior inference of the latent variables.

For salience estimation, we propose an unsupervised data reconstruction framework, which jointly considers the reconstruction for latent semantic space and observed term vector space. Therefore, we can capture the salience of sentences from these two different and complementary vector spaces.

Thereafter, the VAEs-based latent semantic model is integrated into the sentence salience estimation component in a unified fashion, and the whole framework can be trained jointly by back-propagation via multi-task learning.
Experimental results on the benchmark datasets DUC and TAC show that our framework achieves better performance than the state-of-the-art models.
著者Piji Li, Zihao Wang, Wai Lam, Zhaochun Ren, Lidong Bing
會議名稱The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
會議地點San Francisco, California
會議論文集題名Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
頁次3497 - 3503

上次更新時間 2021-08-02 於 15:23