Aim of this project is to determine whether a word in a sentence is being used metaphorically, and uses a metaphoric mapping to interpret it. A metaphor is a figure of speech in which the unfamiliar is expressed in terms of the familiar. However, it is not always necessary that the word may be used as a metaphor. It is very difficult for the systems to understand the metaphor. Proposed system extracts relevant words from a sentence and comparison with a pool of stored metaphor's in the database. If artificial intelligence is used in this project, we can increase the accuracy of the system.
There are many proven systems in the market which identify metaphors. One of them is CorMet. It is a metaphorical corpus based system for mappings between concepts.It does this by finding systematic variations in domain-specific selectional preferences, which are inferred from large, dynamically mined Internet corpora. Metaphors are transferred from source to a target domain, thus by making metaphors in the both source and target domain equal. The verbs that select for a concept in the source domain tend to select for its metaphorical equivalent in the target domain. This regularity, detectable with a shallow linguistic analysis, is used to find the metaphorical inter concept mappings, which can then be used to infer the existence of higher level conventional metaphors.
Metaphor Extraction Engine searching the web for Domain Corpora
CorMet uses manually vetted precompiled online corpora ((Kucera 1992; Marcus, Santorini, and Marcinkiewicz 1993) or use Internet hierarchically structured indices like Yahoo’s ontology and Google to draw metaphors. Each index entry contains a small number of high-quality links to relevant Web pages, but this is not helpful, because CorMet requires many documents, and those documents need not be of more than moderate quality. CorMet obtains documents by submitting queries to the Google search engine. There are two types of queries: one to fetch any domain-specific documents and another to fetch domain-specific documents that contain a particular verb. The first kind of query consists of a conjunction of from two to five randomly selected domain keywords.Domain keywords are words characteristic of a domain, supplied by the user as an input. For the STOCKS domain, a reasonable set of keywords is NSE, BSE, stocks, bonds, NASDAQ, Dow, investment, finance. Each query incorporates only a few keywords in order to maximize the number of distinct possible queries.
For domain specific documents containing a particular verb queries are composed of a combination of domain specific terms and a disjunction of forms of the verb that are more likely to be verbs than other parts of speech. For the verb attack, for instance, acceptable forms are attacked and attacking, but not attack and attacks, which are more likely to be nouns.