Neural Latent Extractive Document Summarization

Xingxing Zhang, Maria Lapata, Furu Wei, Ming Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 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.
Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Place of PublicationBrussels, Belgium
PublisherAssociation for Computational Linguistics
Number of pages6
Publication statusPublished - Nov 2018
Event2018 Conference on Empirical Methods in Natural Language Processing - Square Meeting Center, Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018


Conference2018 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2018
Internet address


Dive into the research topics of 'Neural Latent Extractive Document Summarization'. Together they form a unique fingerprint.

Cite this