SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.07036 · 2018

Learning to Extract Coherent Summary via Deep Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed neural coherence model can efficiently capture the cross-sentence coherence patterns. Using the combined output of the neural coherence model and ROUGE package as the reward, we design a reinforcement learning method to train a proposed neural extractive summarizer which is named Reinforced Neural Extractive Summarization (RNES) model. The RNES model learns to optimize coherence and informative importance of the summary simultaneously. Experimental results show that the proposed RNES outperforms existing baselines and achieves state-of-the-art performance in term of ROUGE on CNN/Daily Mail dataset. The qualitative evaluation indicates that summaries produced by RNES are more coherent and readable.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1804.07036")
get_code_for_paper("1804.07036")
have("1804.07036")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1804.07036.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1804.07036.svg)](https://syntology.ai/paper/1804.07036)

Connect an agent — have() is free.