Abstract | ||
---|---|---|
Metaphor is highly frequent in language, which makes its computational processing indispensable for real-world NLP applications addressing semantic tasks. Previous approaches to metaphor modeling rely on task-specific hand-coded knowledge and operate on a limited domain or a subset of phenomena. We present the first integrated open-domain statistical model of metaphor processing in unrestricted text. Our method first identifies metaphorical expressions in running text and then paraphrases them with their literal paraphrases. Such a text-to-text model of metaphor interpretation is compatible with other NLP applications that can benefit from metaphor resolution. Our approach is minimally supervised, relies on the state-of-the-art parsing and lexical acquisition technologies distributional clustering and selectional preference induction, and operates with a high accuracy. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1162/COLI_a_00124 | Computational Linguistics |
Keywords | DocType | Volume |
metaphor interpretation,metaphor resolution,metaphor processing,integrated open-domain statistical model,metaphor modeling,nlp application,text-to-text model,computational processing indispensable,statistical metaphor processing,unrestricted text,real-world nlp application,statistical model | Journal | 39 |
Issue | ISSN | Citations |
2 | 0891-2017 | 12 |
PageRank | References | Authors |
0.96 | 74 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ekaterina Shutova | 1 | 228 | 21.51 |
Simone Teufel | 2 | 1066 | 82.38 |
Anna Korhonen | 3 | 1336 | 92.50 |