Year: 2018
Type: conference-paper
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 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.
DOI: 10.18653/v1/d18-1088
Authors: Xingxing Zhang, Mirella Lapata, Furu Wei, Ming Zhou
Institutions: Microsoft Research Asia (China), University of Edinburgh
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: H2020 European Research Council
OpenAlex ID: W2888556271