Exemplar-based word-space model for compositionality detection: shared task system description

Siva Reddy; Diana McCarthy; Suresh Kumar Manandhar; Spandana Gella

Exemplar-based word-space model for compositionality detection: shared task system description

Siva Reddy, Diana McCarthy, Suresh Kumar Manandhar, Spandana Gella

Computer Science

Research output: Contribution to conference › Paper

Abstract

In this paper, we highlight the problems of polysemy in word space models of compositionality detection. Most models represent each word as a single prototype-based vector without addressing polysemy. We propose an exemplar-based model which is designed to handle polysemy. This model is tested for compositionality detection and it is found to outperform existing prototype-based models. We have participated in the shared task (Biemann and Giesbrecht, 2011) and our best performing exemplar-model is ranked first in two types of evaluations and second in two other evaluations.

Original language	English
Pages	54-60
Publication status	Published - 2011
Event	Distributional Semantics and Compositionality (DISCO 2011) - Oregon, Portland, United States Duration: 24 Jun 2011 → …

Workshop

Workshop	Distributional Semantics and Compositionality (DISCO 2011)
Country/Territory	United States
City	Portland
Period	24/06/11 → …

Cite this

@conference{623894ed08794701873a5c75ee17b01a,

title = "Exemplar-based word-space model for compositionality detection: shared task system description",

abstract = "In this paper, we highlight the problems of polysemy in word space models of compositionality detection. Most models represent each word as a single prototype-based vector without addressing polysemy. We propose an exemplar-based model which is designed to handle polysemy. This model is tested for compositionality detection and it is found to outperform existing prototype-based models. We have participated in the shared task (Biemann and Giesbrecht, 2011) and our best performing exemplar-model is ranked first in two types of evaluations and second in two other evaluations.",

author = "Siva Reddy and Diana McCarthy and Manandhar, {Suresh Kumar} and Spandana Gella",

year = "2011",

language = "English",

pages = "54--60",

note = "Distributional Semantics and Compositionality (DISCO 2011) ; Conference date: 24-06-2011",

}

TY - CONF

T1 - Exemplar-based word-space model for compositionality detection: shared task system description

AU - Reddy, Siva

AU - McCarthy, Diana

AU - Manandhar, Suresh Kumar

AU - Gella, Spandana

PY - 2011

Y1 - 2011

N2 - In this paper, we highlight the problems of polysemy in word space models of compositionality detection. Most models represent each word as a single prototype-based vector without addressing polysemy. We propose an exemplar-based model which is designed to handle polysemy. This model is tested for compositionality detection and it is found to outperform existing prototype-based models. We have participated in the shared task (Biemann and Giesbrecht, 2011) and our best performing exemplar-model is ranked first in two types of evaluations and second in two other evaluations.

AB - In this paper, we highlight the problems of polysemy in word space models of compositionality detection. Most models represent each word as a single prototype-based vector without addressing polysemy. We propose an exemplar-based model which is designed to handle polysemy. This model is tested for compositionality detection and it is found to outperform existing prototype-based models. We have participated in the shared task (Biemann and Giesbrecht, 2011) and our best performing exemplar-model is ranked first in two types of evaluations and second in two other evaluations.

M3 - Paper

SP - 54

EP - 60

T2 - Distributional Semantics and Compositionality (DISCO 2011)

Y2 - 24 June 2011

ER -