Multi-Document Summarization using Distributed Bag-of-Words Model
This addresses the problem of efficiently summarizing large document sets for users needing quick insights, though it appears incremental as it builds on existing centroid and bag-of-words methods.
The paper tackles multi-document summarization by proposing an unsupervised centroid-based framework using a distributed bag-of-words model to select summary sentences that minimize reconstruction error, achieving significant performance gains over state-of-the-art baselines on two datasets.
As the number of documents on the web is growing exponentially, multi-document summarization is becoming more and more important since it can provide the main ideas in a document set in short time. In this paper, we present an unsupervised centroid-based document-level reconstruction framework using distributed bag of words model. Specifically, our approach selects summary sentences in order to minimize the reconstruction error between the summary and the documents. We apply sentence selection and beam search, to further improve the performance of our model. Experimental results on two different datasets show significant performance gains compared with the state-of-the-art baselines.