Entity-Aware Abstractive Multi-Document Summarization

Entities and their mentions convey significant semantic information in documents. In multidocument summarization, the same entity may appear across different documents. Capturing such cross-document entity information can be beneficial - intuitively, it allows the system to aggregate diverse useful information around the same entity for better summarization. In this paper, we present EMSum, an entityaware model for abstractive multi-document summarization. Our model augments the classical Transformer-based encoder-decoder framework with a heterogeneous graph consisting of text units and entities as nodes, which allows rich cross-document information to be captured. In the decoding process, we design a novel two-level attention mechanism, allowing the model to deal with saliency and redundancy issues explicitly. Our model can also be used together with pre-trained language models, arriving at improved performance. We conduct comprehensive experiments on the standard datasets and the results show the effectiveness of our approach.