Introduction to the special issue on learning semantics

Antoine Bordes, Léon Bottou, Ronan Collobert, Dan Roth, Jason Weston, Luke Zettlemoyer

Research output: Contribution to journalReview article

Abstract

The 2014 Special Issue of Machine Learning discusses several papers on learning semantics. The first paper of the special issue, 'From Machine Learning to Machine Reasoning' by Léon Bottou is an essay which attempts to bridge trainable systems, like neural networks, and sophisticated 'all-purpose' inference mechanisms, such as logical or probabilistic inference. The paper 'Learning Perceptually Grounded Word Meanings from Unaligned Parallel Data' by Stefanie Tellex, Pratiksha Thaker, Joshua Joseph and Nicholas Roy describes an approach to map natural language commands to actions for a forklift control task. The paper 'Interactive Relational Reinforcement Learning of Concept Semantics' by Matthias Nickles and Achim Rettinger presents a Relational Reinforcement Learning (RRL) approach for learning denotational concept semantics using symbolic interaction of artificial agents with human users.

Original languageEnglish (US)
Pages (from-to)127-131
Number of pages5
JournalMachine Learning
Volume94
Issue number2
DOIs
StatePublished - Feb 1 2014

Fingerprint

Semantics
Reinforcement learning
Learning systems
Neural networks

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Bordes, A., Bottou, L., Collobert, R., Roth, D., Weston, J., & Zettlemoyer, L. (2014). Introduction to the special issue on learning semantics. Machine Learning, 94(2), 127-131. https://doi.org/10.1007/s10994-013-5381-4

Introduction to the special issue on learning semantics. / Bordes, Antoine; Bottou, Léon; Collobert, Ronan; Roth, Dan; Weston, Jason; Zettlemoyer, Luke.

In: Machine Learning, Vol. 94, No. 2, 01.02.2014, p. 127-131.

Research output: Contribution to journalReview article

Bordes, A, Bottou, L, Collobert, R, Roth, D, Weston, J & Zettlemoyer, L 2014, 'Introduction to the special issue on learning semantics', Machine Learning, vol. 94, no. 2, pp. 127-131. https://doi.org/10.1007/s10994-013-5381-4
Bordes A, Bottou L, Collobert R, Roth D, Weston J, Zettlemoyer L. Introduction to the special issue on learning semantics. Machine Learning. 2014 Feb 1;94(2):127-131. https://doi.org/10.1007/s10994-013-5381-4
Bordes, Antoine ; Bottou, Léon ; Collobert, Ronan ; Roth, Dan ; Weston, Jason ; Zettlemoyer, Luke. / Introduction to the special issue on learning semantics. In: Machine Learning. 2014 ; Vol. 94, No. 2. pp. 127-131.
@article{5f825c29d43c46fca1f35b4942bd279f,
title = "Introduction to the special issue on learning semantics",
abstract = "The 2014 Special Issue of Machine Learning discusses several papers on learning semantics. The first paper of the special issue, 'From Machine Learning to Machine Reasoning' by L{\'e}on Bottou is an essay which attempts to bridge trainable systems, like neural networks, and sophisticated 'all-purpose' inference mechanisms, such as logical or probabilistic inference. The paper 'Learning Perceptually Grounded Word Meanings from Unaligned Parallel Data' by Stefanie Tellex, Pratiksha Thaker, Joshua Joseph and Nicholas Roy describes an approach to map natural language commands to actions for a forklift control task. The paper 'Interactive Relational Reinforcement Learning of Concept Semantics' by Matthias Nickles and Achim Rettinger presents a Relational Reinforcement Learning (RRL) approach for learning denotational concept semantics using symbolic interaction of artificial agents with human users.",
author = "Antoine Bordes and L{\'e}on Bottou and Ronan Collobert and Dan Roth and Jason Weston and Luke Zettlemoyer",
year = "2014",
month = "2",
day = "1",
doi = "10.1007/s10994-013-5381-4",
language = "English (US)",
volume = "94",
pages = "127--131",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Introduction to the special issue on learning semantics

AU - Bordes, Antoine

AU - Bottou, Léon

AU - Collobert, Ronan

AU - Roth, Dan

AU - Weston, Jason

AU - Zettlemoyer, Luke

PY - 2014/2/1

Y1 - 2014/2/1

N2 - The 2014 Special Issue of Machine Learning discusses several papers on learning semantics. The first paper of the special issue, 'From Machine Learning to Machine Reasoning' by Léon Bottou is an essay which attempts to bridge trainable systems, like neural networks, and sophisticated 'all-purpose' inference mechanisms, such as logical or probabilistic inference. The paper 'Learning Perceptually Grounded Word Meanings from Unaligned Parallel Data' by Stefanie Tellex, Pratiksha Thaker, Joshua Joseph and Nicholas Roy describes an approach to map natural language commands to actions for a forklift control task. The paper 'Interactive Relational Reinforcement Learning of Concept Semantics' by Matthias Nickles and Achim Rettinger presents a Relational Reinforcement Learning (RRL) approach for learning denotational concept semantics using symbolic interaction of artificial agents with human users.

AB - The 2014 Special Issue of Machine Learning discusses several papers on learning semantics. The first paper of the special issue, 'From Machine Learning to Machine Reasoning' by Léon Bottou is an essay which attempts to bridge trainable systems, like neural networks, and sophisticated 'all-purpose' inference mechanisms, such as logical or probabilistic inference. The paper 'Learning Perceptually Grounded Word Meanings from Unaligned Parallel Data' by Stefanie Tellex, Pratiksha Thaker, Joshua Joseph and Nicholas Roy describes an approach to map natural language commands to actions for a forklift control task. The paper 'Interactive Relational Reinforcement Learning of Concept Semantics' by Matthias Nickles and Achim Rettinger presents a Relational Reinforcement Learning (RRL) approach for learning denotational concept semantics using symbolic interaction of artificial agents with human users.

UR - http://www.scopus.com/inward/record.url?scp=84894302977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894302977&partnerID=8YFLogxK

U2 - 10.1007/s10994-013-5381-4

DO - 10.1007/s10994-013-5381-4

M3 - Review article

AN - SCOPUS:84894302977

VL - 94

SP - 127

EP - 131

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 2

ER -