tailieunhanh - Báo cáo khoa học: "Models of Metaphor in NLP"

Automatic processing of metaphor can be clearly divided into two subtasks: metaphor recognition (distinguishing between literal and metaphorical language in a text) and metaphor interpretation (identifying the intended literal meaning of a metaphorical expression). Both of them have been repeatedly addressed in NLP. This paper is the first comprehensive and systematic review of the existing computational models of metaphor, the issues of metaphor annotation in corpora and the available resources. . | Models of Metaphor in NLP Ekaterina Shutova Computer Laboratory University of Cambridge 15 JJ Thomson Avenue Cambridge CB3 0FD UK Abstract Automatic processing of metaphor can be clearly divided into two subtasks metaphor recognition distinguishing between literal and metaphorical language in a text and metaphor interpretation identifying the intended literal meaning of a metaphorical expression . Both of them have been repeatedly addressed in NLP. This paper is the first comprehensive and systematic review of the existing computational models of metaphor the issues of metaphor annotation in corpora and the available resources. 1 Introduction Our production and comprehension of language is a multi-layered computational process. Humans carry out high-level semantic tasks effortlessly by subconsciously employing a vast inventory of complex linguistic devices while simultaneously integrating their background knowledge to reason about reality. An ideal model of language understanding would also be capable of performing such high-level semantic tasks. However a great deal of NLP research to date focuses on processing lower-level linguistic information such as . part-of-speech tagging discovering syntactic structure of a sentence parsing coreference resolution named entity recognition and many others. Another cohort of researchers set the goal of improving applicationbased statistical inference . for recognizing textual entailment or automatic summarization . In contrast there have been fewer attempts to bring the state-of-the-art NLP technologies together to model the way humans use language to frame high-level reasoning processes such as for example creative thought. The majority of computational approaches to figurative language still exploit the ideas articulated three decades ago Wilks 1978 Lakoff and Johnson 1980 Fass 1991 and often rely on taskspecific hand-coded knowledge. However recent work on lexical semantics and lexical .