Neural Latent Extractive Document Summarization
This work addresses a key bottleneck in extractive summarization for NLP researchers, though it is incremental as it builds on existing methods.
The authors tackled the problem of suboptimal sentence-level labels in extractive document summarization by proposing a latent variable model that directly uses gold summaries for training, achieving competitive performance on the CNN/Dailymail dataset.
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.