Iterative Document Representation Learning Towards Summarization with Polishing

EMNLP 2018 Xiuying ChenShen GaoChongyang TaoYan SongDongyan ZhaoRui Yan

In this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents. Current summarization approaches read through a document only once to generate a document representation, resulting in a sub-optimal representation... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Extractive Document Summarization CNN / Daily Mail ITS ROUGE-2 12.6 # 3
Extractive Document Summarization CNN / Daily Mail ITS ROUGE-1 30.80 # 1