Multi-Document Summarization Using A* Search and Discriminative Learning

@inproceedings{Aker2010MultiDocumentSU,
  title={Multi-Document Summarization Using A* Search and Discriminative Learning},
  author={Ahmet Aker and Trevor Cohn and Robert J. Gaizauskas},
  booktitle={EMNLP},
  year={2010}
}
In this paper we address two key challenges for extractive multi-document summarization: the search problem of finding the best scoring summary and the training problem of learning the best model parameters. We propose an A* search algorithm to find the best extractive summary up to a given length, which is both optimal and efficient to run. Further, we propose a discriminative training algorithm which directly maximises the quality of the best summary, rather than assuming a sentence-level… CONTINUE READING