vix.ing · top · new · best · stats

GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state

2022/11/18 by Junyi Bian, Xiaodi Huang, Bian, Junyi +5 · 1 citation
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2211.10247

openalex publication_date 2022/11/18 · openalex created_date 2022/11/28 · openalex updated_date 2026/07/28

Abstract

Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose GoSum, a novel graph and reinforcement learning based extractive model for long-paper summarization. In particular, GoSum encodes sentence states in reinforcement learning by building a heterogeneous graph for each input document at different discourse levels. An edge in the graph reflects the discourse hierarchy of a document for restraining the semantic drifts across section boundaries. We evaluate GoSum on two datasets of scientific articles summarization: PubMed and arXiv. The experimental results have demonstrated that GoSum achieve state-of-the-art results compared with strong baselines of both extractive and abstractive models. The ablation studies further validate that the performance of our GoSum benefits from the use of discourse information.

Cited by

Related