Home > Research > Publications & Outputs > Conceptual combination with PUNC
View graph of relations

Conceptual combination with PUNC

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Conceptual combination with PUNC. / Lynott, Dermot; Tagalakis, Georgios; Keane, Markt.
In: Artificial Intelligence Review, Vol. 21, No. 3-4, 06.2004, p. 353-374.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Lynott, D, Tagalakis, G & Keane, M 2004, 'Conceptual combination with PUNC', Artificial Intelligence Review, vol. 21, no. 3-4, pp. 353-374. https://doi.org/10.1023/B:AIRE.0000036263.74312.50

APA

Lynott, D., Tagalakis, G., & Keane, M. (2004). Conceptual combination with PUNC. Artificial Intelligence Review, 21(3-4), 353-374. https://doi.org/10.1023/B:AIRE.0000036263.74312.50

Vancouver

Lynott D, Tagalakis G, Keane M. Conceptual combination with PUNC. Artificial Intelligence Review. 2004 Jun;21(3-4):353-374. doi: 10.1023/B:AIRE.0000036263.74312.50

Author

Lynott, Dermot ; Tagalakis, Georgios ; Keane, Markt. / Conceptual combination with PUNC. In: Artificial Intelligence Review. 2004 ; Vol. 21, No. 3-4. pp. 353-374.

Bibtex

@article{a9e3651e8ade4f898776c785fe705067,
title = "Conceptual combination with PUNC",
abstract = "Noun-noun compounds play a key role in the growth of language. In this article we present a system for producing and understanding noun-noun compounds (PUNC). PUNC is based on the Constraint theory of conceptual combination and the C-3 model. The new model incorporates the primary constraints of the Constraint theory in an integrated fashion, creating a cognitively plausible mechanism of interpreting noun-noun phrases. It also tries to overcome algorithmic limitations of the C-3 model in being more efficient in its computational complexity, and deal with a wider span of empirical phenomena, such as dimensions of word familiarity. We detail the model, including knowledge representation and interpretation production mechanisms. We show that by integrating the constraints of the Constraint theory of conceptual combination and prioritizing the knowledge available within a concept's representation, PUNC can not only generate interpretations that reflect those produced by people, but also mirror the differences in processing times for understanding familiar, similar and novel word combinations.",
keywords = "COMPREHENSION, plausibility, LANGUAGE, familiarity, diagnosticity, ALIGNMENT, conceptual combination, noun-noun compounds, MODELS, informativeness, SEMANTIC SIMILARITY",
author = "Dermot Lynott and Georgios Tagalakis and Markt. Keane",
year = "2004",
month = jun,
doi = "10.1023/B:AIRE.0000036263.74312.50",
language = "English",
volume = "21",
pages = "353--374",
journal = "Artificial Intelligence Review",
issn = "0269-2821",
publisher = "Springer Netherlands",
number = "3-4",
note = "14th Artificial Intelligence and Cognitive Science Conference (AICS 2003) ; Conference date: 17-09-2003 Through 19-09-2003",

}

RIS

TY - JOUR

T1 - Conceptual combination with PUNC

AU - Lynott, Dermot

AU - Tagalakis, Georgios

AU - Keane, Markt.

PY - 2004/6

Y1 - 2004/6

N2 - Noun-noun compounds play a key role in the growth of language. In this article we present a system for producing and understanding noun-noun compounds (PUNC). PUNC is based on the Constraint theory of conceptual combination and the C-3 model. The new model incorporates the primary constraints of the Constraint theory in an integrated fashion, creating a cognitively plausible mechanism of interpreting noun-noun phrases. It also tries to overcome algorithmic limitations of the C-3 model in being more efficient in its computational complexity, and deal with a wider span of empirical phenomena, such as dimensions of word familiarity. We detail the model, including knowledge representation and interpretation production mechanisms. We show that by integrating the constraints of the Constraint theory of conceptual combination and prioritizing the knowledge available within a concept's representation, PUNC can not only generate interpretations that reflect those produced by people, but also mirror the differences in processing times for understanding familiar, similar and novel word combinations.

AB - Noun-noun compounds play a key role in the growth of language. In this article we present a system for producing and understanding noun-noun compounds (PUNC). PUNC is based on the Constraint theory of conceptual combination and the C-3 model. The new model incorporates the primary constraints of the Constraint theory in an integrated fashion, creating a cognitively plausible mechanism of interpreting noun-noun phrases. It also tries to overcome algorithmic limitations of the C-3 model in being more efficient in its computational complexity, and deal with a wider span of empirical phenomena, such as dimensions of word familiarity. We detail the model, including knowledge representation and interpretation production mechanisms. We show that by integrating the constraints of the Constraint theory of conceptual combination and prioritizing the knowledge available within a concept's representation, PUNC can not only generate interpretations that reflect those produced by people, but also mirror the differences in processing times for understanding familiar, similar and novel word combinations.

KW - COMPREHENSION

KW - plausibility

KW - LANGUAGE

KW - familiarity

KW - diagnosticity

KW - ALIGNMENT

KW - conceptual combination

KW - noun-noun compounds

KW - MODELS

KW - informativeness

KW - SEMANTIC SIMILARITY

U2 - 10.1023/B:AIRE.0000036263.74312.50

DO - 10.1023/B:AIRE.0000036263.74312.50

M3 - Journal article

VL - 21

SP - 353

EP - 374

JO - Artificial Intelligence Review

JF - Artificial Intelligence Review

SN - 0269-2821

IS - 3-4

T2 - 14th Artificial Intelligence and Cognitive Science Conference (AICS 2003)

Y2 - 17 September 2003 through 19 September 2003

ER -