Left-Brain/Right-Brain Multi-Document Summarization

By John M. Conroy. 2004

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Alex Kulesza
2. J. Bilmes
3. B. Taskar
4. Hui-Ching Lin
5. Yoshua Bengio
6. Li Deng
7. Mirella Lapata
8. Percy Liang

Citations in the corpus

• A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization (2006, methodology): “65 is a supervised HMM system [4], requring training data and parameter adjustment, while the SUMCF summarizers are non-supervised and totally data-driven.”
• Summarization Using Reinforcement Learning (2012, unknown): “• PEER65: This is the best performing system in task 2 of the DUC2004 competition in terms of ROUGE-1 proposed by Conroy et al. (2004).”
• Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources (2007, methodology): “The meth-ods include binary classifiers (Kupiec et al., 1995), Markov models (Conroy et al., 2004), Bayesian methods (Daum´e III and Marcu, 2005; Aone et al., 1998), and heuristic methods to determine feature weights (Schiffman, 2002; Lin and Hovy, 2002).”
• Fear the REAPER: A System for Automatic Multi-Document Summarization with Reinforcement Learning (2014, background): “(Ryang and Abekawa, 2012), MCKP (Takamura and Okumura, 2009), PEER65 (Conroy et al., 2004) , and GREEDY (Ryang and Abekawa, 2012) algorithms on the same task.”
• Multi-document Summarization via Budgeted Maximization of Submodular Functions (2010, methodology): “Our approach also outperforms the best system (Conroy et al., 2004), peer code 65 in the DUC’04 evaluation although not as significant ( p 0 .”
• Learning Determinantal Point Processes (2011, methodology): “In our experiments Y(X) contains all sentences in the cluster, though preprocessing can also be used to try to improve the candidate set (Conroy et al., 2004).”