Distributional relational networks

Andre Freitas; João C.P. Da Silva; Seán O'Riain; Edward Curry

Distributional relational networks

Andre Freitas
, João C.P. Da Silva
, Seán O'Riain
, Edward Curry

Computer Science

University of Galway
Federal University of Rio de Janeiro

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

4 Citations (Scopus)

Abstract

This work introduces Distributional Relational Networks (DRNs), a Knowledge Representation (KR) framework which focuses on allowing semantic approximations over large-scale and heterogeneous knowledge bases. The proposed model uses the distributional semantics information embedded in large text/data corpora to provide a comprehensive and principled solution for semantic approximation. DRNs can be applied to open domain knowledge bases and can be used as a KR model for commonsense reasoning. Experimental results show the suitability of DRNs as a semantically flexible KR framework.

Original language	English
Title of host publication	How Should Intelligence Be Abstracted in AI Research
Subtitle of host publication	MDPs, Symbolic Representations, Artificial Neural Networks, or? - Papers from the AAAI Fall Symposium, Technical Report
Publisher	AI Access Foundation
Pages	22-27
Number of pages	6
ISBN (Print)	9781577356400
Publication status	Published - 2013
Event	2013 AAAI Fall Symposium - Arlington, VA, United States Duration: 15 Nov 2013 → 17 Nov 2013

Publication series

Name	AAAI Fall Symposium - Technical Report
Volume	FS-13-02

Conference

Conference	2013 AAAI Fall Symposium
Country/Territory	United States
City	Arlington, VA
Period	15/11/13 → 17/11/13

Cite this

Freitas, A., Da Silva, J. C. P., O'Riain, S., & Curry, E. (2013). Distributional relational networks. In How Should Intelligence Be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial Neural Networks, or? - Papers from the AAAI Fall Symposium, Technical Report (pp. 22-27). (AAAI Fall Symposium - Technical Report; Vol. FS-13-02). AI Access Foundation.

@inproceedings{38e59e7a49eb46d1b8a92932ef5d0f1b,

title = "Distributional relational networks",

abstract = "This work introduces Distributional Relational Networks (DRNs), a Knowledge Representation (KR) framework which focuses on allowing semantic approximations over large-scale and heterogeneous knowledge bases. The proposed model uses the distributional semantics information embedded in large text/data corpora to provide a comprehensive and principled solution for semantic approximation. DRNs can be applied to open domain knowledge bases and can be used as a KR model for commonsense reasoning. Experimental results show the suitability of DRNs as a semantically flexible KR framework.",

author = "Andre Freitas and \{Da Silva\}, \{Jo{\~a}o C.P.\} and Se{\'a}n O'Riain and Edward Curry",

year = "2013",

language = "English",

isbn = "9781577356400",

series = "AAAI Fall Symposium - Technical Report",

publisher = "AI Access Foundation",

pages = "22--27",

booktitle = "How Should Intelligence Be Abstracted in AI Research",

note = "2013 AAAI Fall Symposium ; Conference date: 15-11-2013 Through 17-11-2013",

}

Freitas, A, Da Silva, JCP, O'Riain, S & Curry, E 2013, Distributional relational networks. in How Should Intelligence Be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial Neural Networks, or? - Papers from the AAAI Fall Symposium, Technical Report. AAAI Fall Symposium - Technical Report, vol. FS-13-02, AI Access Foundation, pp. 22-27, 2013 AAAI Fall Symposium, Arlington, VA, United States, 15/11/13.

Distributional relational networks. / Freitas, Andre; Da Silva, João C.P.; O'Riain, Seán et al.
How Should Intelligence Be Abstracted in AI Research: MDPs, Symbolic Representations, Artificial Neural Networks, or? - Papers from the AAAI Fall Symposium, Technical Report. AI Access Foundation, 2013. p. 22-27 (AAAI Fall Symposium - Technical Report; Vol. FS-13-02).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Distributional relational networks

AU - Freitas, Andre

AU - Da Silva, João C.P.

AU - O'Riain, Seán

AU - Curry, Edward

PY - 2013

Y1 - 2013

N2 - This work introduces Distributional Relational Networks (DRNs), a Knowledge Representation (KR) framework which focuses on allowing semantic approximations over large-scale and heterogeneous knowledge bases. The proposed model uses the distributional semantics information embedded in large text/data corpora to provide a comprehensive and principled solution for semantic approximation. DRNs can be applied to open domain knowledge bases and can be used as a KR model for commonsense reasoning. Experimental results show the suitability of DRNs as a semantically flexible KR framework.

AB - This work introduces Distributional Relational Networks (DRNs), a Knowledge Representation (KR) framework which focuses on allowing semantic approximations over large-scale and heterogeneous knowledge bases. The proposed model uses the distributional semantics information embedded in large text/data corpora to provide a comprehensive and principled solution for semantic approximation. DRNs can be applied to open domain knowledge bases and can be used as a KR model for commonsense reasoning. Experimental results show the suitability of DRNs as a semantically flexible KR framework.

UR - https://www.scopus.com/pages/publications/84898921130

M3 - Conference Publication

AN - SCOPUS:84898921130

SN - 9781577356400

T3 - AAAI Fall Symposium - Technical Report

SP - 22

EP - 27

BT - How Should Intelligence Be Abstracted in AI Research

PB - AI Access Foundation

T2 - 2013 AAAI Fall Symposium

Y2 - 15 November 2013 through 17 November 2013

ER -

Distributional relational networks

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this