Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
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 -