Ranking with Recursive Neural Networks and Its Application to Multi-Document Summarization

Authors

  • Ziqiang Cao Peking University
  • Furu Wei Microsoft Research Asia
  • Li Dong Beihang University
  • Sujian Li Peking University
  • Ming Zhou Microsoft Research Asia

Abstract

We develop a Ranking framework upon Recursive Neural Networks (R2N2) to rank sentences for multi-document summarization. It formulates the sentence ranking task as a hierarchical regression process, which simultaneously measures the salience of a sentence and its constituents (e.g., phrases) in the parsing tree. This enables us to draw on word-level to sentence-level supervisions derived from reference summaries.In addition, recursive neural networks are used to automatically learn ranking features over the tree, with hand-crafted feature vectors of words as inputs. Hierarchical regressions are then conducted with learned features concatenating raw features.Ranking scores of sentences and words are utilized to effectively select informative and non-redundant sentences to generate summaries.Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that R2N2 outperforms state-of-the-art extractive summarization approaches.

Downloads

Published

2015-02-19

How to Cite

Cao, Z., Wei, F., Dong, L., Li, S., & Zhou, M. (2015). Ranking with Recursive Neural Networks and Its Application to Multi-Document Summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/9490

Issue

Section

Main Track: NLP and Knowledge Representation