TY - GEN
T1 - Literal and metaphorical sense identification through concrete and abstract context
AU - Turney, Peter D.
AU - Neuman, Yair
AU - Assaf, Dan
AU - Cohen, Yohai
PY - 2011/10/3
Y1 - 2011/10/3
N2 - Metaphor is ubiquitous in text, even in highly technical text. Correct inference about textual entailment requires computers to distinguish the literal and metaphorical senses of a word. Past work has treated this problem as a classical word sense disambiguation task. In this paper, we take a new approach, based on research in cognitive linguistics that views metaphor as a method for transferring knowledge from a familiar, well-understood, or concrete domain to an unfamiliar, less understood, or more abstract domain. This view leads to the hypothesis that metaphorical word usage is correlated with the degree of abstractness of the word's context. We introduce an algorithm that uses this hypothesis to classify a word sense in a given context as either literal (denotative) or metaphorical (connotative). We evaluate this algorithm with a set of adjective-noun phrases (e.g., in dark comedy, the adjective dark is used metaphorically; in dark hair, it is used literally) and with the TroFi (Trope Finder) Example Base of literal and nonliteral usage for fifty verbs. We achieve state-of-the-art performance on both datasets.
AB - Metaphor is ubiquitous in text, even in highly technical text. Correct inference about textual entailment requires computers to distinguish the literal and metaphorical senses of a word. Past work has treated this problem as a classical word sense disambiguation task. In this paper, we take a new approach, based on research in cognitive linguistics that views metaphor as a method for transferring knowledge from a familiar, well-understood, or concrete domain to an unfamiliar, less understood, or more abstract domain. This view leads to the hypothesis that metaphorical word usage is correlated with the degree of abstractness of the word's context. We introduce an algorithm that uses this hypothesis to classify a word sense in a given context as either literal (denotative) or metaphorical (connotative). We evaluate this algorithm with a set of adjective-noun phrases (e.g., in dark comedy, the adjective dark is used metaphorically; in dark hair, it is used literally) and with the TroFi (Trope Finder) Example Base of literal and nonliteral usage for fifty verbs. We achieve state-of-the-art performance on both datasets.
UR - http://www.scopus.com/inward/record.url?scp=80053255626&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80053255626
SN - 1937284115
SN - 9781937284114
T3 - EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 680
EP - 690
BT - EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2011
Y2 - 27 July 2011 through 31 July 2011
ER -