Topic Augmented Generator for Abstractive Summarization
arXiv:1908.07026
Abstract
Steady progress has been made in abstractive summarization with attention-based sequence-to-sequence learning models. In this paper, we propose a new decoder where the output summary is generated by conditioning on both the input text and the latent topics of the document. The latent topics, identified by a topic model such as LDA, reveals more global semantic information that can be used to bias the decoder to generate words. In particular, they enable the decoder to have access to additional word co-occurrence statistics captured at document corpus level. We empirically validate the advantage of the proposed approach on both the CNN/Daily Mail and the WikiHow datasets. Concretely, we attain strongly improved ROUGE scores when compared to state-of-the-art models.
References in corpus (8)
- Teaching Machines to Read and Comprehend
- A Deep Reinforced Model for Abstractive Summarization
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- WikiHow: A Large Scale Text Summarization Dataset
- Modeling Coverage for Neural Machine Translation
- Get To The Point: Summarization with Pointer-Generator Networks
- Efficient Summarization with Read-Again and Copy Mechanism
- Topic-Guided Variational Autoencoders for Text Generation