Papperoni

2006

Machine Reading

Etzioni, Banko, Cafarella

citations

Cite Score

AI summary

This paper introduces the concept of Machine Reading (MR) and presents the KnowItAll and TextRunner systems for unsupervised information extraction from the web, utilizing techniques like self-supervision and generic extraction patterns to achieve large-scale knowledge acquisition, while highlighting challenges like inconsistency and synonymy in extracted data.

Main Contributions

Introduces the concept of "Machine Reading" as the automatic, unsupervised understanding of text.
Presents the KnowItAll system, which learns to label its own training examples using a small set of domain-independent extraction patterns.
Introduces the TextRunner system, which seamlessly extracts information from each sentence it encounters in a self-supervised fashion.
Demonstrates how NLP techniques can be harnessed to begin to understand text in a domain-independent and unsupervised manner.
Highlights the problem of recursive learning---how an MR system can leverage the information it has read to date to enhance its understanding of the next sentences it encounters.

Abstract

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.

Citation Graph

Loading graph...

References [9]

Sort:

Filter:

[1]The PASCAL Recognising Textual Entailment Challenge

Ido Dagan, O. Glickman, Bernardo Magnini - 2005

19 papers in library cite

Google Scholar

It's very nice how they had the foresight to create a challenge that became relevant like 10 years later.

[2]Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews

P. D. Turney - 2002

3 papers in library cite

Google Scholar

[3]A Probabilistic Model of Redundancy in Information Extraction

D. Downey, Oren Etzioni, S. Soderland - 2005

1 paper in library cites

Google Scholar

[4]Extracting Patterns and Relations From the World Wide Web

S. Brin - 1998

1 paper in library cites

Google Scholar

[5]Personal Communication

N. Friedland - 2005

1 paper in library cites

Google Scholar

[6]Reading the Web: A Breakthrough Goal for AI. Celebrating Twenty-Five Years of AAAI: Notes From the AAAI-05 and IAAI-05 Conferences

T. Mitchell - 2005

1 paper in library cites

Google Scholar

[7]Relational Web Search

M. Cafarella, M. Banko, Oren Etzioni - 2006

1 paper in library cites

Google Scholar

[8]Snowball: Extracting Relations From Large Plain-Text Collections

E. Agichtein, L. Gravano - 2000

1 paper in library cites

Google Scholar

[9]Unsupervised Named-Entity Extraction From the Web: An Experimental Study

Oren Etzioni, M. Cafarella, D. Downey, A. Popescu, T. Shaked, S. Soderland, D. S. Weld, A. Yates - 2005

1 paper in library cites

Google Scholar

Cited by

papers in your library

Cites

papers in your library

Read

on November 29, 2025

It's not bad, it's just uninteresting and doesn't really bring anything new.