BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:gromgull

The blue social bookmark and publication sharing system.

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Scaling textual inference to the web

by: Stefan Schoenmackers, Oren Etzioni, and Daniel S. Weld

In: EMNLP '08: Proceedings of the Conference on Empirical Methods in Natural Language Processing Morristown, NJ, USA: Association for Computational Linguistics (2008) , p. 79--88.

Resources (URL, PDF, PS...)

URL:	http://portal.acm.org/citation.cfm?id=1613727

Most Web-based Q/A systems work by finding pages that contain an explicit answer to a question. These systems are helpless if the answer has to be inferred from multiple sentences, possibly on different pages. To solve this problem, we introduce the Holmes system, which utilizes textual inference TI over tuples extracted from text. Whereas previous work on TI e.g., the literature on textual entailment has been applied to paragraph-sized texts, Holmes utilizes knowledge-based model construction to scale TI to a corpus of 117 million Web pages. Given only a few minutes, Holmes doubles recall for example queries in three disparate domains geography, business, and nutrition. Importantly, Holmes's runtime is linear in the size of its input corpus due to a surprising property of many textual relations in the Web corpus---they are äpproximately" functional in a well-defined sense.

Description

Scaling textual inference to the web

BibTeX record

@inproceedings{schoenmackers08,
  abstract = {Most Web-based Q/A systems work by finding pages that contain an explicit answer to a question. These systems are helpless if the answer has to be inferred from multiple sentences, possibly on different pages. To solve this problem, we introduce the Holmes system, which utilizes textual inference (TI) over tuples extracted from text. Whereas previous work on TI (e.g., the literature on textual entailment) has been applied to paragraph-sized texts, Holmes utilizes knowledge-based model construction to scale TI to a corpus of 117 million Web pages. Given only a few minutes, Holmes doubles recall for example queries in three disparate domains (geography, business, and nutrition). Importantly, Holmes's runtime is linear in the size of its input corpus due to a surprising property of many textual relations in the Web corpus---they are "approximately" functional in a well-defined sense.},
  added-at = {2009-11-18T17:02:49.000+0100},
  address = {Morristown, NJ, USA},
  author = {Schoenmackers, Stefan and Etzioni, Oren and Weld, Daniel S.},
  biburl = {http://www.bibsonomy.org/bibtex/2af67c1da5575db58d06ec9841aa44bac/gromgull},
  booktitle = {EMNLP '08: Proceedings of the Conference on Empirical Methods in Natural Language Processing},
  description = {Scaling textual inference to the web},
  interhash = {41f9bc006f06783e921b535921057b37},
  intrahash = {af67c1da5575db58d06ec9841aa44bac},
  keywords = {inference machine-learning question-answering unsupervised-learning web},
  location = {Honolulu, Hawaii},
  pages = {79--88},
  publisher = {Association for Computational Linguistics},
  timestamp = {2009-11-18T17:02:49.000+0100},
  title = {Scaling textual inference to the web},
  url = {http://portal.acm.org/citation.cfm?id=1613727},
  year = 2008
}

Endnote record

%0 Conference Paper
%1 schoenmackers08
%A Schoenmackers, Stefan
%A Etzioni, Oren
%A Weld, Daniel S.
%B EMNLP '08: Proceedings of the Conference on Empirical Methods in Natural Language Processing
%C Morristown, NJ, USA
%D 2008
%I Association for Computational Linguistics
%K 
%P 79--88
%T Scaling textual inference to the web
%U http://portal.acm.org/citation.cfm?id=1613727
%X Most Web-based Q/A systems work by finding pages that contain an explicit answer to a question. These systems are helpless if the answer has to be inferred from multiple sentences, possibly on different pages. To solve this problem, we introduce the Holmes system, which utilizes textual inference (TI) over tuples extracted from text. Whereas previous work on TI (e.g., the literature on textual entailment) has been applied to paragraph-sized texts, Holmes utilizes knowledge-based model construction to scale TI to a corpus of 117 million Web pages. Given only a few minutes, Holmes doubles recall for example queries in three disparate domains (geography, business, and nutrition). Importantly, Holmes's runtime is linear in the size of its input corpus due to a surprising property of many textual relations in the Web corpus---they are "approximately" functional in a well-defined sense.

BibSonomy :: publication ::

Scaling textual inference to the web

Resources (URL, PDF, PS...)

Abstract

Description

BibTeX record

Endnote record