Title :
A New Feature-Fusion Sentence Selecting Strategy for Query-Focused Multi-document Summarization
Author :
He, Tingting ; Li, Fang ; Shao, Wei ; Chen, Jinguang ; Ma, Liang
Author_Institution :
Dept. of Comput. Sci., Huazhong Normal Univ., Wuhan
Abstract :
The most important step of query-focused extractive summarization is deciding which sentences are appropriately included in the final summary. In this paper, we propose a feature fusion based sentence selecting strategy, to identify the sentences with high query-relevance and high information density. We score each sentence by computing its similarity and Skip-Bigram co-occurrence with query. These two features can measure the query-relevance from content and structure respectively. Then, we re-score the sentences using the information density feature gained from a text graph which can provide position information. And finally, we adopt MMR for sentence extracting. Experimental results indicate that this method is effective in capturing important sentences. The ROUGE-2 and ROUGE-SU4 scores are 0.0640 and 0.1233, which are at the top of the DUC2005 scores.
Keywords :
abstracting; graph theory; query processing; relevance feedback; text analysis; DUC2005 scores; MMR; ROUGE-2; ROUGE-SU4; Skip-Bigram co-occurrence; feature-fusion sentence selecting strategy; query-focused multidocument summarization; query-relevance; sentence extracting; text graph; Computer science; Computer science education; Cost function; Data mining; Fuses; Helium; Information retrieval; Information technology; Network neutrality; Voting; Skip-Bigram; feature fusion; position information;
Conference_Titel :
Advanced Language Processing and Web Information Technology, 2008. ALPIT '08. International Conference on
Conference_Location :
Dalian Liaoning
Print_ISBN :
978-0-7695-3273-8
DOI :
10.1109/ALPIT.2008.45