Topic-Selective Graph Network for Topic-Focused Summarization
This work addresses the need for topic-focused summarization to cater to different readers, representing an incremental improvement over existing prompt-based methods.
The paper tackles the problem of generating summaries that focus on specific topics by addressing the disturbance from non-relevant sentences and limited cross-interaction in existing methods, proposing a topic-arc recognition objective and topic-selective graph network that achieve state-of-the-art performance on NEWTS and COVIDET datasets.
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.