Hand-written instructions are a common way of disseminating how-to information. However, studies have shown that written instructions are difficult to follow. Users could benefit from a system that understands hand-written instructions and provides users with assistance in following them. While general natural language understanding is extremely difficult, we believe that understanding should be possible in the more limited domain of how-to instructions. In this paper, we present an investigation of parsing and understanding hand-written instructions. We began by collecting a corpus of instructions for 43 web-based tasks. A qualitative study of these instructions revealed that despite a wide variation in quality, there is a common set of verbs and nouns that are used to describe tasks on web sites. We then implemented and compared three how-to instruction interpreters: one based on keyword matching, one based on a grammar, and one using machine learning. The best of these interpreters achieved 53% accuracy in interpreting instructions in our corpus.
By: Tessa Lau; Clemens Drews; Jeffrey Nichols
Published in: RJ10438 in 2008
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .