Simple Unsupervised Summarization by Contextual Matching
arXiv:1907.13337
Abstract
We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by using a product-of-experts criteria these are enough for maintaining continuous contextual matching while maintaining output fluency. Experiments on both abstractive and extractive sentence summarization data sets show promising results of our method without being exposed to any paired data.
References in corpus (8)
- A Deep Reinforced Model for Abstractive Summarization
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Online and Linear-Time Attention by Enforcing Monotonic Alignments
- Towards better decoding and language model integration in sequence to sequence models
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- The Neural Noisy Channel
- Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder
- Online Segment to Segment Neural Transduction