2006 MachineReading

Jump to navigation Jump to search

Subject Headings: Information Extraction, Machine Reading


Cited By



1. Introduction

The time is ripe for the AI community to set its sights on Machine Reading - the automatic, unsupervised understanding of text. In this paper, we place the notion of “Machine Reading” in context, describe progress towards this goal by the KnowItAll research group at the University of Washington, and highlight several central research questions.

By “understanding text” I mean the formation of a coherent set of beliefs based on a textual corpus and a background theory. Because the text and the background theory may be inconsistent, it is natural to express the resultant beliefs, and the reasoning process in probabilistic terms. A key problem is that many of the beliefs of interest are only implied by the text in combination with a background theory. To recall Roger Schank’s old example, if the text states that a person left a restaurant after a satisfactory meal, it is reasonable to infer that he is likely to have paid the bill and left a tip. Thus, inference is an integral part of text understanding.


  • Eugene Agichtein, and Gravano, L., (2000). Snowball: Extracting Relations from Large Plain-Text Collections. Proceedings of the Fifth ACM International Conference on Digital Libraries.
  • Sergey Brin. (1998). “Extracting Patterns and Relations from the World Wide Web.” In: Proceedings of the WebDB Workshop.
  • Cafarella M., Banko M., and Oren Etzioni, (2006). Relational Web Search. University of Washington Technical Report, UW-CSE-2006-04-02.
  • Dagan, I., Glickman, O., and Bernardo Magnini (2005). The PASCAL Recognising Textual Entailment Challenge. In: Proceedings of the first PASCAL Challenges Workshop on Recognising Textual Entailment, Southampton, U.K.: Pattern Analysis, Statistical Modelling and Computational Learning, Inc.
  • Downey, D., Oren Etzioni, and Soderland, S. (2005). A Probabilistic Model of Redundancy in Information Extraction. In: Proceedings of the 19th International Joint Conference on Artificial Intelligence, 1034-1041. Edinburgh, Scotland: International Joint Conference on Artificial Intelligence, Inc.
  • Oren Etzioni, Cafarella, M., Downey, D., Popescu, A., Shaked, T., Soderland, S., Weld, D. S., and Yates, A. (2005). Unsupervised Named-Entity Extraction from the Web: An Experimental Study. Artificial Intelligence, 165(1):91-134.
  • Friedland, N. (2005). Personal Communication.
  • Tom M. Mitchell. (2005). Reading the Web: A Breakthrough Goal for AI. Celebrating Twenty-Five Years of AAAI: Notes from the AAAI-05 and IAAI-05 Conferences. AI Magazine 26(3):12-16.
  • Peter D. Turney (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 417-424. Philadelphia, Penn.: Association for Computational Linguistics, Inc.


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2006 MachineReadingMichael J. Cafarella
Oren Etzioni
Michele Banko
Machine Readinghttp://turing.cs.washington.edu/papers/aaai06.pdf