# Topic-Selective Graph Network for Topic-Focused Summarization

## TL;DR

This paper introduces a topic-selective graph network with a topic-arc recognition objective to improve topic-focused summarization, effectively filtering non-relevant information and achieving state-of-the-art results on benchmark datasets.

## Contribution

The paper proposes a novel topic-arc recognition objective and a topic-selective graph network to enhance topic-focused summarization beyond prompt-guided methods.

## Key findings

- Achieves state-of-the-art performance on NEWTS and COVIDET datasets.
- Effectively discriminates relevant topics for improved summarization.
- Outperforms existing prompt-guided topic summarization methods.

## Abstract

Due to the success of the pre-trained language model (PLM), existing PLM-based summarization models show their powerful generative capability. However, these models are trained on general-purpose summarization datasets, leading to generated summaries failing to satisfy the needs of different readers. To generate summaries with topics, many efforts have been made on topic-focused summarization. However, these works generate a summary only guided by a prompt comprising topic words. Despite their success, these methods still ignore the disturbance of sentences with non-relevant topics and only conduct cross-interaction between tokens by attention module. To address this issue, we propose a topic-arc recognition objective and topic-selective graph network. First, the topic-arc recognition objective is used to model training, which endows the capability to discriminate topics for the model. Moreover, the topic-selective graph network can conduct topic-guided cross-interaction on sentences based on the results of topic-arc recognition. In the experiments, we conduct extensive evaluations on NEWTS and COVIDET datasets. Results show that our methods achieve state-of-the-art performance.