Neural Latent Extractive Document Summarization
arXiv:1808.07187
Abstract
Extractive summarization models require sentence-level labels, which are usually created heuristically (e.g., with rule-based methods) given that most summarization datasets only have document-summary pairs. Since these labels might be suboptimal, we propose a latent variable extractive model where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries. During training the loss comes \emph{directly} from gold summaries. Experiments on the CNN/Dailymail dataset show that our model improves over a strong extractive baseline trained on heuristically approximated labels and also performs competitively to several recent models.
arXiv commentto appear in EMNLP 2018
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Recurrent Neural Network Regularization
- A Deep Reinforced Model for Abstractive Summarization
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Neural Summarization by Extracting Sentences and Words