Paper: Using Word-Sense Disambiguation Methods to Classify Web Queries by Intent

ACL ID D09-1148
Title Using Word-Sense Disambiguation Methods to Classify Web Queries by Intent
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009
Authors

Three methods are proposed to classify queries by intent (CQI), e.g., navigational, informational, commercial, etc. Follow- ing mixed-initiative dialog systems, search engines should distinguish navigational queries where the user is taking the ini- tiative from other queries where there are more opportunities for system initiatives (e.g., suggestions, ads). The query in- tent problem has a number of useful appli- cations for search engines, affecting how many (if any) advertisements to display, which results to return, and how to ar- range the results page. Click logs are used as a substitute for annotation. Clicks on ads are evidence for commercial in- tent; other types of clicks are evidence for other intents. We start with a simple Na¨ıve Bayes baseline that works well when there is ...