Paper: PNR2: Ranking Sentences with Positive and Negative Reinforcement for Query-Oriented Update Summarization

ACL ID C08-1062
Title PNR2: Ranking Sentences with Positive and Negative Reinforcement for Query-Oriented Update Summarization
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2008
Authors
  • Wenjie Li (Hong Kong Polytechnic University, Hung Hom Hong Kong)
  • Furu Wei (Hong Kong Polytechnic University, Hung Hom Hong Kong; Wuhan University, Wuhan China)
  • Qin Lu (Wuhan University, Wuhan China)
  • Yanxiang He

Query-oriented update summarization is an emerging summarization task very recently. It brings new challenges to the sentence ranking algorithms that require not only to locate the important and query-relevant information, but also to capture the new information when document collections evolve. In this paper, we propose a novel graph based sentence ranking algorithm, namely PNR2, for update summarization. Inspired by the intuition that “a sentence receives a positive influence from the sentences that correlate to it in the same collection, whereas a sentence receives a negative influence from the sentences that correlates to it in the different (perhaps previously read) collection”, PNR2 models both the positive and the negative mutual reinforcement in the ranking ...