Learning relational features with backward random walks

Ni Lao; Einat Minkov; William W. Cohen

doi:10.3115/v1/p15-1065

Learning relational features with backward random walks

Ni Lao, Einat Minkov, William W. Cohen

Department of Information Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The path ranking algorithm (PRA) has been recently proposed to address relational classification and retrieval tasks at large scale. We describe Cor-PRA, an enhanced system that can model a larger space of relational rules, including longer relational rules and a class of first order rules with constants, while maintaining scalability. We describe and test faster algorithms for searching for these features. A key contribution is to leverage backward random walks to efficiently discover these types of rules. An empirical study is conducted on the tasks of graph-based knowledge base inference, and person named entity extraction from parsed text. Our results show that learning paths with constants improves performance on both tasks, and that modeling longer paths dramatically improves performance for the named entity extraction task.

Original language	English
Title of host publication	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	666-675
Number of pages	10
ISBN (Electronic)	9781941643723
DOIs	https://doi.org/10.3115/v1/p15-1065
State	Published - 2015
Event	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China Duration: 26 Jul 2015 → 31 Jul 2015

Publication series

Name	ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Volume	1

Conference

Conference	53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Country/Territory	China
City	Beijing
Period	26/07/15 → 31/07/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computationl Linguisticss.

ASJC Scopus subject areas

Artificial Intelligence
Software

Access to Document

10.3115/v1/p15-1065

Cite this

Lao, N., Minkov, E., & Cohen, W. W. (2015). Learning relational features with backward random walks. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (pp. 666-675). (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-1065

Lao, Ni ; Minkov, Einat ; Cohen, William W. / Learning relational features with backward random walks. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 666-675 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference).

@inproceedings{991743a1199642e19d365604ada20118,

title = "Learning relational features with backward random walks",

abstract = "The path ranking algorithm (PRA) has been recently proposed to address relational classification and retrieval tasks at large scale. We describe Cor-PRA, an enhanced system that can model a larger space of relational rules, including longer relational rules and a class of first order rules with constants, while maintaining scalability. We describe and test faster algorithms for searching for these features. A key contribution is to leverage backward random walks to efficiently discover these types of rules. An empirical study is conducted on the tasks of graph-based knowledge base inference, and person named entity extraction from parsed text. Our results show that learning paths with constants improves performance on both tasks, and that modeling longer paths dramatically improves performance for the named entity extraction task.",

author = "Ni Lao and Einat Minkov and Cohen, {William W.}",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computationl Linguisticss.; 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 ; Conference date: 26-07-2015 Through 31-07-2015",

year = "2015",

doi = "10.3115/v1/p15-1065",

language = "English",

series = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "666--675",

booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",

address = "United States",

}

Lao, N, Minkov, E & Cohen, WW 2015, Learning relational features with backward random walks. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference, vol. 1, Association for Computational Linguistics (ACL), pp. 666-675, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 26/07/15. https://doi.org/10.3115/v1/p15-1065

Learning relational features with backward random walks. / Lao, Ni; Minkov, Einat; Cohen, William W.
ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 666-675 (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning relational features with backward random walks

AU - Lao, Ni

AU - Minkov, Einat

AU - Cohen, William W.

PY - 2015

Y1 - 2015

N2 - The path ranking algorithm (PRA) has been recently proposed to address relational classification and retrieval tasks at large scale. We describe Cor-PRA, an enhanced system that can model a larger space of relational rules, including longer relational rules and a class of first order rules with constants, while maintaining scalability. We describe and test faster algorithms for searching for these features. A key contribution is to leverage backward random walks to efficiently discover these types of rules. An empirical study is conducted on the tasks of graph-based knowledge base inference, and person named entity extraction from parsed text. Our results show that learning paths with constants improves performance on both tasks, and that modeling longer paths dramatically improves performance for the named entity extraction task.

AB - The path ranking algorithm (PRA) has been recently proposed to address relational classification and retrieval tasks at large scale. We describe Cor-PRA, an enhanced system that can model a larger space of relational rules, including longer relational rules and a class of first order rules with constants, while maintaining scalability. We describe and test faster algorithms for searching for these features. A key contribution is to leverage backward random walks to efficiently discover these types of rules. An empirical study is conducted on the tasks of graph-based knowledge base inference, and person named entity extraction from parsed text. Our results show that learning paths with constants improves performance on both tasks, and that modeling longer paths dramatically improves performance for the named entity extraction task.

UR - http://www.scopus.com/inward/record.url?scp=84943785112&partnerID=8YFLogxK

U2 - 10.3115/v1/p15-1065

DO - 10.3115/v1/p15-1065

M3 - Conference contribution

AN - SCOPUS:84943785112

T3 - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

SP - 666

EP - 675

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015

Y2 - 26 July 2015 through 31 July 2015

ER -

Lao N, Minkov E, Cohen WW. Learning relational features with backward random walks. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 666-675. (ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference). doi: 10.3115/v1/p15-1065

Learning relational features with backward random walks

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this