Query-Oriented Keyphrase Extraction
Conference Proceeding Article
People often issue informational queries to search engines to find out more about some entities or events. While a Wikipedia-like summary would be an ideal answer to such queries, not all queries have a corresponding Wikipedia entry. In this work we propose to study query-oriented keyphrase extraction, which can be used to assist search results summarization. We propose a general method for keyphrase extraction for our task, where we consider both phraseness and informativeness. We discuss three criteria for phraseness and four ways to compute informativeness scores. Using a large Wikipedia corpus and 40 queries, our empirical evaluation shows that using a named entity-based phraseness criterion and a language model-based informativeness score gives the best performance on our task. This method also outperforms two state-of-the-art baseline methods.
Keyphrase extraction, phraseness, informativeness, language model
Databases and Information Systems
Data Management and Analytics
Information Retrieval Technology: 8th Asia Information Retrieval Societies Conference (AIRS'12)
City or Country
QIU, Minghui; LI, Yaliang; and JIANG, Jing.
Query-Oriented Keyphrase Extraction. (2012). Information Retrieval Technology: 8th Asia Information Retrieval Societies Conference (AIRS'12). 7675, 64-75. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/1709