Query Snowball: A Co-occurrence-based Approach to Multi-document Summarization for Question Answering

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a new method for query-oriented extractive multi-document summarization. To enrich the information need representation of a given query, we build a co-occurrence graph to obtain words that augment the original query terms. We then formulate the summarization problem as a Maximum Coverage Problem with Knapsack Constraints based on word pairs rather than single words. Our experiments with the NTCIR ACLIA question answering test collections show that our method achieves a pyramid F3-score of up to 0.313, a 36% improvement over a baseline using Maximal Marginal Relevance.

• 2012-06-29

著者

• Manabu Okumura

  Precision And Intelligence Laboratory Tokyo Institute Of Technology

• Tetsuya Sakai

  Microsoft Research Asia

• Hajime Morita

  Tokyo Institute Of Technology

関連論文

• Active Learning with Partially Annotated Sequence
• Japanese Hyponymy Extraction based on a Term Similarity Graph
• Query Snowball: A Co-occurrence-based Approach to Multi-document Summarization for Question Answering
• The Reusability of a Diversified Search Test Collection
• One Click One Revisited: Enhancing Evaluation based on Information Units
• The Reusability of a Diversified Search Test Collection
• One Click One Revisited: Enhancing Evaluation based on Information Units
• Web Search Evaluation with Informational and Navigational Intents (Preprint)
• A Preview of the NTCIR-10 INTENT-2 Results
• A Preview of the NTCIR-10 INTENT-2 Results
• How Intuitive Are Diversified Search Metrics? Concordance Test Results for the Diversity U-measures
• How Intuitive Are Diversified Search Metrics? Concordance Test Results for the Diversity U-measures

もっと見る 閉じる

スポンサーリンク