Supervising the Centroid Baseline for Extractive Multi-Document Summarization
This work addresses the need for better summarization tools in multi-document and multilingual contexts, but it appears incremental as it builds upon existing centroid-based methods.
The paper tackled the problem of extractive multi-document summarization by refining the centroid method with beam search and an attention model, resulting in improved performance across multiple datasets, including in multilingual scenarios, though specific numerical gains are not detailed in the abstract.
The centroid method is a simple approach for extractive multi-document summarization and many improvements to its pipeline have been proposed. We further refine it by adding a beam search process to the sentence selection and also a centroid estimation attention model that leads to improved results. We demonstrate this in several multi-document summarization datasets, including in a multilingual scenario.