2020 · 73 citations · 42 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingText AnalyticsAttention NetworksData SummarizationDeep LearningLanguage ModelingText SummarizationCentralityDocument SummarizationEncoder-decoder ArchitecturesNeural SummarizationNeural Text SummarizationSummarizationSummarization DatasetsTransformer Language Models
Copy module has been widely equipped in the recent abstractive summarization models, which facilitates the decoder to extract words from the source into the summary. Generally, the encoder-decoder attention is served as the copy distribution, while how to guarantee that important words in the source are copied remains a challenge. In this work, we propose a Transformer-based model to enhance the copy mechanism. Specifically, we identify the importance of each source word based on the degree centrality with a directed graph built by the self-attention layer in the Transformer. We use the centrality of each source word to guide the copy process explicitly. Experimental results show that the self-attention graph provides useful guidance for the copy distribution. Our proposed models significantly outperform the baseline methods on the CNN/Daily Mail dataset and the Gigaword dataset.
42
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Centrality in social networks conceptual clarification
Linton C. Freeman · Social Networks · 1978 · 16.9K citations
The PageRank Citation Ranking : Bringing Order to the Web
Lawrence M. Page, Sergey Brin, Rajeev Motwani et al. · 1999 · 12.7K citations