Unsupervised Metaphor Paraphrasing using a Vector Space Model
نویسندگان
چکیده
We present the first fully unsupervised approach to metaphor interpretation, and a system that produces literal paraphrases for metaphorical expressions. Such a form of interpretation is directly transferable to other NLP applications that can benefit from a metaphor processing component. Our method is different from previous work in that it does not rely on any manually annotated data or lexical resources. First, our method computes candidate paraphrases according to the context in which the metaphor appears, using a vector space model. It then uses a selectional preference model to measure the degree of literalness of the paraphrases. The system identifies correct paraphrases with a precision of 0.52 at top rank, which is a promising result for a fully unsupervised approach.
منابع مشابه
Metaphor Interpretation Using Paraphrases Extracted from the Web
Interpreting metaphor is a hard but important problem in natural language processing that has numerous applications. One way to address this task is by finding a paraphrase that can replace the metaphorically used word in a given context. This approach has been previously implemented only within supervised frameworks, relying on manually constructed lexical resources, such as WordNet. In contra...
متن کاملMELODI: A Supervised Distributional Approach for Free Paraphrasing of Noun Compounds
This paper describes the system submitted by the MELODI team for the SemEval-2013 Task 4: Free Paraphrases of Noun Compounds (Hendrickx et al., 2013). Our approach combines the strength of an unsupervised distributional word space model with a supervised maximum-entropy classification model; the distributional model yields a feature representation for a particular compound noun, which is subseq...
متن کاملEncoding syntactic dependencies by vector permutation
Distributional approaches are based on a simple hypothesis: the meaning of a word can be inferred from its usage. The application of that idea to the vector space model makes possible the construction of a WordSpace in which words are represented by mathematical points in a geometric space. Similar words are represented close in this space and the definition of “word usage” depends on the defin...
متن کاملAutomatic Metaphor Interpretation as a Paraphrasing Task
We present a novel approach to metaphor interpretation and a system that produces literal paraphrases for metaphorical expressions. Such a representation is directly transferable to other applications that can benefit from a metaphor processing component. Our method is distinguished from the previous work in that it does not rely on any hand-crafted knowledge about metaphor, but in contrast emp...
متن کاملA Novel Distributional Approach to Multilingual Conceptual Metaphor Recognition
We present a novel approach to the problem of multilingual conceptual metaphor recognition. Our approach extends recent work in conceptual metaphor discovery by combining a complex methodology for facet-based concept induction with a distributional vector space model of linguistic and conceptual metaphor. In the evaluation of our system in English, Spanish, Russian, and Farsi, we experiment wit...
متن کامل