Paper: Spice it up? Mining Refinements to Online Instructions from User Generated Content

ACL ID P12-1057
Title Spice it up? Mining Refinements to Online Instructions from User Generated Content
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

There are a growing number of popular web sites where users submit and review instruc- tions for completing tasks as varied as build- ing a table and baking a pie. In addition to pro- viding their subjective evaluation, reviewers often provide actionable refinements. These refinements clarify, correct, improve, or pro- vide alternatives to the original instructions. However, identifying and reading all relevant reviews is a daunting task for a user. In this paper, we propose a generative model that jointly identifies user-proposed refinements in instruction reviews at multiple granularities, and aligns them to the appropriate steps in the original instructions. Labeled data is not read- ily available for these tasks, so we focus on the unsupervised setting. In experiments in the recipe dom...