Query-Oriented Keyphrase Extraction

• Main Authors: QIU, Minghui, LI, Yaliang, JIANG, Jing
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2012
• Subjects: Keyphrase extraction; phraseness; informativeness; language model; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/1709
• Institution: Singapore Management University

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.