Computational Metaphor Identification: a Method for Identifying Conceptual Metaphors in Written Text
نویسندگان
چکیده
While much research has pursued the development of computational models of metaphorical and analogical reasoning in controlled contexts, less work has been conducted on model capturing less structured, everyday relational reasoning. This paper describes computational metaphor identification (CMI), which uses computational linguistic techniques to identify patterns in written text indicative of potential conceptual metaphors. The paper presents an overview of CMI, followed by sample results from two different corpora: middle school students' science writing and political blogs from during the 2008 US election. These results demonstrate CMI's capacity to identify linguistic patterns potentially indicative of deep conceptual metaphors that could subtly yet powerfully influence reasoning.
منابع مشابه
Automatic Identification of Conceptual Metaphors With Limited Knowledge
Full natural language understanding requires identifying and analyzing the meanings of metaphors, which are ubiquitous in both text and speech. Over the last thirty years, linguistic metaphors have been shown to be based on more general conceptual metaphors, partial semantic mappings between disparate conceptual domains. Though some achievements have been made in identifying linguistic metaphor...
متن کاملGenerating Conceptual Metaphors from Proposition Stores
Contemporary research on computational processing of linguistic metaphors is divided into two main branches: metaphor recognition and metaphor interpretation. We take a different line of research and present an automated method for generating conceptual metaphors from linguistic data. Given the generated conceptual metaphors, we find corresponding linguistic metaphors in corpora. In this paper,...
متن کاملUsing Metaphor Analysis: MIP and Beyond
Metaphor analysis is a way of obtaining understanding of a text by identifying and analysing the metaphors used in it. Metaphor analysis, as usually described, uses the researcher’s intuition as a means of identifying the metaphors. MIP, the Metaphor Identification Procedure, uses a more valid and repeatable way of finding the metaphors. MIP may be applied in a way that will produce a quantitat...
متن کاملComparing Semantic Role Labeling with Typed Dependency Parsing in Computational Metaphor Identification
Most computational approaches to metaphor have focused on discerning between metaphorical and literal text. Recent work on computational metaphor identification (CMI) instead seeks to identify overarching conceptual metaphors by mapping selectional preferences between source and target corpora. This paper explores using semantic role labeling (SRL) in CMI. Its goals are two-fold: first, to demo...
متن کاملFrom Embodiment to Metaphor: A Study on Social Cognitive Development and Conceptual Metaphor in Persian-Speaking Children
This study explores the metaphoric comprehension of normal Persian-speaking children, as well as theories of cognitive development and cultural and social impacts. The researchers discuss the improvement of the understanding of ontological conceptual metaphors through age growth and cognitive development, and how it helps to expand children’s thoughts and knowledge of the world. In this study, ...
متن کامل