No abstract

No abstract

We describe an information seeking assistant for the world wide web. This agent, called WebWatcher, interactively helps users locate desired information by employing learned knowledge about which hyperlinks are likely to lead to the target information. Our primary focus to date has been on two issues: (1) organizing WebWatcher to provide interactive advice to Mosaic users while logging their successful and unsuccessful searches as training data, and (2) incorporating machine learning methods to automatically acquire knowledge for selecting an appropriate hyperlink given the current web page viewed by the user and the user's information goal. We describe the initial design of WebWatcher, and the results of our preliminary learning experiments. 6 Machine Learning Information Services Tlds ~ti~ being rnaintu~cd bF the ML Groul~ at the AustrianResea~.h Institute [or Arti0cial Int cll~ence (OPAl), Vienna, Austria It is far from complete and is being opdatcd on anin'cgular basis. Pleas e direct comment/ su~estions/...to Gelll~d Widmer {gerh~dCc~,cd,~nil'ie,¢~:.) To ~' out our experlnncnt~l WcbWatcher s catch as slstant, click lj_ _e~_ GeJmral ML l,tfot'trtatio,t Sotu'ces

Personal software assistants that help users with tasks like finding information, scheduling calendars, or managing work-flow will require significant customization to each individual user. For example, an assistant that helps schedule a particular user's calendar will have to know that user's scheduling preferences. This paper explores the potential of machine learning methods to automatically create and maintain such customized knowledge for personal software assistants. We describe the design of one particular learning assistant: a calendar manager, called CAP (Calendar APprentice), that learns user scheduling preferences from experience. Results are summarized from approximately five user-years of experience, during which CAP has learned an evolving set of several thousand rules that characterize the scheduling preferences of its users. Based on this experience, we suggest that machine learning methods may play an important role in future personal software assistants.

Recent work on the problem of detecting synonymy through corpus analysis has used the Test of English as a Foreign Language (TOEFL) as a benchmark. However, this test involves as few as 80 questions, prompting questions regarding the statistical significance of reported results. We overcome this limitation by generating a TOEFL-like test using WordNet, containing thousands of questions and composed only of words occurring with sufficient corpus frequency to support sound distributional comparisons. Experiments with this test lead us to a similarity measure which significantly outperforms the best proposed to date. Analysis suggests that a strength of this measure is its relative robustness against polysemy.