Advanced summarization based on intents

1. A method of summarizing content using weighted Formal Concept Analysis (wFCA) comprising:

(i) identifying, by a processor, a plurality of keywords in said content based on parts of speech, wherein said content comprises a plurality of sentences and said plurality of keywords;

(ii) identifying, by said processor, an ambiguous keyword from said plurality of keywords, wherein said ambiguous keyword has more than one meaning;

(iii) generating, by said processor, a plurality of concepts based on (a) said plurality of keywords as objects, and (b) categories associated with said plurality of keywords as attributes, and wherein said categories are obtained from a knowledge base;

(iv) computing, by said processor, a score for each concept of said plurality of concepts;

(v) disambiguating, by said processor, said ambiguous keyword based on said score to obtain a right meaning of said ambiguous keyword in context of a sentence in said content;

(vi) identifying, by said processor, an association between said plurality of keywords and at least one sentence in said content;

(vii) determining, by said processor, a weight associated with each keyword of said plurality of keywords based on a number of associations of said each keyword with said at least one sentence in said content;

(viii) identifying, by said processor, a set of associated keywords that are specific to each sentence of said at least one sentence, from said plurality of keywords;

(ix) determining, by said processor, a weight associated with each sentence of said at least one sentence based on a weight of each keyword of said set of associated keywords;

(x) selecting at least one sentence from said plurality of sentences in said content based on said weight associated with said each sentence; and

(xi) generating, by said processor, a summary of said content, wherein said summary comprises said at least one sentence selected based on said weight.

2. The method of claim 1 , further comprising generating a lattice that comprises said plurality of concepts.

3. The method of claim 2 , wherein said categories are not arranged based on a hierarchy.

4. The method of claim 3 , wherein a score for a concept of said plurality of concepts is computed based on (i) a number of associations of said concept with other concepts in said lattice, and (ii) said plurality of keywords.

5. The method of claim 2 , further comprising drilling-down a subset of categories associated with said plurality of keywords to obtain a contextual information, wherein said subset of categories are arranged hierarchically, wherein said contextual information indicates an affinity among said plurality of keywords.

6. The method of claim 5 , wherein said contextual information is obtained to disambiguate said ambiguous keyword.

7. The method of claim 1 , further comprising generating a graph to identify said association, wherein said graph comprises a plurality of nodes, wherein each node indicates a sentence in said content.

8. The method of claim 1 , further comprising expanding said summary based on said weight assigned for said each sentence in said content.

9. A non-transitory program storage device readable by computer, and comprising a program of instructions executable by said computer to perform a method for summarizing content using weighted Formal Concept Analysis (wFCA), said method comprising:

(i) identifying, by a processor, a plurality of keywords in said content based on parts of speech, wherein said content comprises a plurality of sentences and said plurality of keywords;

(ii) identifying, by said processor, an ambiguous keyword from said plurality of keywords, wherein said ambiguous keyword has more than one meaning;

(iii) generating, by said processor, a plurality of concepts based on (a) said plurality of keywords as objects, and (b) categories associated with said plurality of keywords as attributes, and wherein said categories are obtained from a knowledge base;

(iv) computing, by said processor, a score for each concept of said plurality of concepts;

(v) disambiguating, by said processor, said ambiguous keyword based on said score to obtain a right meaning of said ambiguous keyword in context of a sentence in said content, wherein a lattice is generated that comprises said plurality of concepts;

(vi) generating, by said processor, a graph to identify an association between said plurality of keywords and at least one sentence in said content, wherein said graph comprises a plurality of nodes, wherein each node indicates a sentence in said content;

(vii) determining, by said processor, a weight associated with each keyword of said plurality of keywords based on a number of associations of said each keyword with said at least one sentence in said content;

(viii) identifying, by said processor, a set of associated keywords that are specific to each sentence of said at least one sentence, from said plurality of keywords;

(ix) determining, by said processor, a weight associated with each sentence of said at least one sentence based on a weight of each keyword of said set of associated keywords;

(x) selecting at least one sentence from said plurality of sentences in said content based on said weight associated with said each sentence; and

(xi) generating, by said processor, a summary of said content, wherein said summary comprises said at least one sentence selected based on said weight.

10. The non-transitory program storage device of claim 9 , wherein said categories are not arranged based on a hierarchy.

11. The non-transitory program storage device of claim 9 , wherein said method further comprises drilling-down a subset of categories associated with said plurality of keywords to obtain a contextual information, wherein said subset of categories are arranged hierarchically, and wherein said contextual information indicates an affinity among said plurality of keywords.

12. A system for summarizing content around a keyword based on weighted Formal Concept Analysis (wFCA) using a content summarization engine, said system comprising: (a) a memory unit that stores (i) a set of modules, and (ii) a database; (b) a display unit; (c) a processor that executes said set of modules, wherein said set of modules comprise:

(i) a keyword identifying module executed by said processor that processes a first input comprising a selection of said keyword around which summarization of said content occurs, wherein said content comprises a plurality of sentences and a plurality of keywords;

(ii) a disambiguating module executed by said processor that

(a) identifies an ambiguous keyword from said plurality of keywords,

wherein said ambiguous keyword has more than one meaning;

(b) generates a plurality of concepts based on (i) said plurality of keywords as objects, and (ii) categories associated with said plurality of keywords as attributes, and wherein said categories are obtained from a knowledge base;

(c) computes a score for each concept of said plurality of concepts; and

(d) disambiguates said ambiguous keyword based on said score to obtain a right meaning of said ambiguous keyword in context of a sentence in said content, wherein a lattice is generated that comprises said plurality of concepts;

(iii) a graph generating module executed by said processor that generates a graph to identify an association between said keyword and at least one sentence in said content, wherein said graph comprises a plurality of nodes, wherein each node indicates a sentence in said content;

(iv) a keyword identifying module executed by said processor that

(a) determines a weight associated with each keyword of said plurality of keywords based on a number of associations of said each keyword with said at least one sentence in said content; and

(b) identifies a set of associated keywords that are specific to each sentence of said at least one sentence, from said plurality of keywords;

(v) a weight assigning module executed by said processor that determines a weight associated with each sentence of said at least one sentence based on a weight of each keyword of said set of associated keywords; and

(vi) an intent building module executed by said processor that

(a) selects at least one sentence from said plurality of sentences in said content based on said weight associated with said each sentence; and

(b) generates a summary of said content around said keyword, wherein said summary comprises said at least one sentence selected based on said weight.

13. The system of claim 12 , wherein said set of modules further comprises an intent expanding module executed by said processor that expands said summary based on said weight assigned for each sentence of said plurality of sentences of said content.