TY - GEN
T1 - Learning distributed word representations for natural logic reasoning
AU - Bowman, Samuel R.
AU - Potts, Christopher
AU - Manning, Christopher D.
N1 - Funding Information:
This research was funded by College of Sciences, University of Central Florida. Original investigations in 1985 and 1986 were supported by the University of Colorado, and in 2000 by the National Geographic Society’s Committee for Exploration and Research, and Peru’s Ministry of Culture. We extend our gratitude to Peru’s Ministry of Culture for project permitting (Oficio 506-2000/DGP-D), and for the cooperation of the Dirección Departamental del INC/San Martín. The emergency conservation project in 2000 was conducted under the auspices of the World Monument Fund, and funded by American Express Corp. The authors wish to acknowledge the assistance of Jeffrey Quilter of Dumbarton Oaks who assisted in securing funds for the archaeological component of the year 2000 project, and the efforts of Mariella Leo of the Asociación Peruana para la Con-servación de la Naturaleza (APECO) for her assistance with fieldwork logistics. Archaeologists participating in the fieldwork include Dr. Thomas J. Lennon, Miguel A. Cornejo Garcia, Dr. Dennis Van Gerven, David O. Ayers, and César Soriano Ríos (1985 and 1986), and Luis Valle Alvarez (2000). We also gratefully acknowledge the dedicated support and assistance of many conservators, residents of Pataz and Los Alisos, as well as the hospitality offered by the citizens of Pataz. JMT acknowledges the support of the Ministry of Culture (DDC) offices in La Libertad and Amazonas. We also thank the laboratory assistance of Christopher Clukay, Maria Russo, and Julia Castwell at UCF, and Kim Law at UWO. We greatly appreciate the discussions and editorial suggestions by many colleagues and AJPA editors and reviewers. Any errors in interpretation are solely those of the authors. UCF Laboratory for Bioarchaeological Sciences publication #1.
Publisher Copyright:
Copyright © 2015. Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2015
Y1 - 2015
N2 - Natural logic offers a powerful relational conception of meaning that is a natural counterpart to distributed semantic representations, which have proven valuable in a wide range of sophisticated language tasks. However, it remains an open question whether it is possible to train distributed representations to support the rich, diverse logical reasoning captured by natural logic. We address this question using two neural network-based models for learning embeddings: plain neural networks and neural tensor networks. Our experiments evaluate the models' ability to learn the basic algebra of natural logic relations from simulated data and from the Word-Net noun graph. The overall positive results are promising for the future of learned distributed representations in the applied modeling of logical semantics.
AB - Natural logic offers a powerful relational conception of meaning that is a natural counterpart to distributed semantic representations, which have proven valuable in a wide range of sophisticated language tasks. However, it remains an open question whether it is possible to train distributed representations to support the rich, diverse logical reasoning captured by natural logic. We address this question using two neural network-based models for learning embeddings: plain neural networks and neural tensor networks. Our experiments evaluate the models' ability to learn the basic algebra of natural logic relations from simulated data and from the Word-Net noun graph. The overall positive results are promising for the future of learned distributed representations in the applied modeling of logical semantics.
UR - http://www.scopus.com/inward/record.url?scp=84987608736&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84987608736&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84987608736
T3 - AAAI Spring Symposium - Technical Report
SP - 10
EP - 13
BT - Knowledge Representation and Reasoning
PB - AI Access Foundation
T2 - 2015 AAAI Spring Symposium
Y2 - 23 March 2015 through 25 March 2015
ER -