BibSonomy :: publication ::

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

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 Web-based Acquisition of Entailment Relations

by: Idan Szpektor, Hristo Tanev, Ido Dagan, and Bonaventura Coppola

In: Proc. Empirical Methods in Natural Language Processing EMNLP Barcelona: (2004) .

Resources (URL, PDF, PS...)

URL:	http://eprints.pascal-network.org/archive/00000797/

Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. However, the scalability of state-of-the-art paraphrase acquisition approaches is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations, an extended model of paraphrases. We focus on increased scalability and generality with respect to prior work, eventually aiming at a full scale knowledge base. Our current implementation of the algorithm takes as its input a verb lexicon and for each verb searches the Web for related syntactic entailment templates. Experiments show promising results with respect to the ultimate goal, achieving much better scalability than prior Web-based methods.

BibTeX record

@inproceedings{Szpektor:2004,
  abstract = {Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. However, the scalability of state-of-the-art paraphrase acquisition approaches is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations, an extended model of paraphrases. We focus on increased scalability and generality with respect to prior work, eventually aiming at a full scale knowledge base. Our current implementation of the algorithm takes as its input a verb lexicon and for each verb searches the Web for related syntactic entailment templates. Experiments show promising results with respect to the ultimate goal, achieving much better scalability than prior Web-based methods.},
  added-at = {2007-12-14T02:47:13.000+0100},
  address = {Barcelona},
  author = {Szpektor, Idan and Tanev, Hristo and Dagan, Ido and Coppola, Bonaventura},
  biburl = {http://www.bibsonomy.org/bibtex/20ac6c3623a4de9e4d7f00d1b7277c82f/diego_ma},
  booktitle = {Proc. Empirical Methods in Natural Language Processing (EMNLP)},
  interhash = {94bb0ef9c6b7f501153d84d28c1aa20e},
  intrahash = {0ac6c3623a4de9e4d7f00d1b7277c82f},
  keywords = {entailment web resources},
  timestamp = {2007-12-14T02:47:13.000+0100},
  title = {Scaling Web-based Acquisition of Entailment Relations},
  url = {http://eprints.pascal-network.org/archive/00000797/},
  year = 2004
}

Endnote record

%0 Conference Paper
%1 Szpektor:2004
%A Szpektor, Idan
%A Tanev, Hristo
%A Dagan, Ido
%A Coppola, Bonaventura
%B Proc. Empirical Methods in Natural Language Processing (EMNLP)
%C Barcelona
%D 2004
%K 
%T Scaling Web-based Acquisition of Entailment Relations
%U http://eprints.pascal-network.org/archive/00000797/
%X Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. However, the scalability of state-of-the-art paraphrase acquisition approaches is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations, an extended model of paraphrases. We focus on increased scalability and generality with respect to prior work, eventually aiming at a full scale knowledge base. Our current implementation of the algorithm takes as its input a verb lexicon and for each verb searches the Web for related syntactic entailment templates. Experiments show promising results with respect to the ultimate goal, achieving much better scalability than prior Web-based methods.

BibSonomy :: publication ::

Scaling Web-based Acquisition of Entailment Relations

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record