Neural Latent Extractive Document Summarization
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.
PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract
Datasets
CNN/Daily Mail
Results from the Paper
Methods
No methods listed for this paper. Add
relevant methods here
