Expansion phrase database for abbreviated terms
A system and method are disclosed for creating a database of expansion phrases for abbreviated terms. The database can be created by submitting a plurality of abbreviated terms and receiving a corresponding results set. The possible expansion phrases can be extracted from the results set, and expansion phrases are selected from the possible expansion phrases using filter rules. The selected expansion phrases may be ranked in a particular order, associated with the abbreviated term, and stored in a database.
1 . A method for creating a database of expansion phrases for abbreviated terms, comprising:
receiving a results set corresponding to an abbreviated term, the results set comprising at least one result;
generating one or more expansion phrases from the results set;
selecting at least one of the generated expansion phrases based on one or more filter rules;
associating the abbreviated term with the at least one selected expansion phrase.
2 . The method according to claim 1 , further comprising ranking the at least one selected expansion phrase.
3 . The method according to claim 2 , further comprising ranking the at least one selected expansion phrase according to the frequency that the at least one selected expansion phrase is found within a query log.
4 . The method according to claim 1 , wherein the results set is received from a similarity graph.
5 . The method according to claim 2 , wherein the results set is received from a search engine.
6 . The method according to claim 5 , further comprising ranking the at least one selected expansion phrase according to the order the at least one selected expansion phrase is found within the results set from the search engine.
7 . The method according to claim 5 , wherein the one or more expansion phrases are generated from at least one of a title of the result and a snippet of the result.
8 . The method according to claim 1 , wherein identifying the at least one selected expansion phrase comprises comparing the at least one abbreviated term to the one or more expansion phrases.
9 . A system for creating a database of expansion phrases for abbreviated terms, comprising:
a phrase generation component for receiving a results set corresponding to an abbreviated term and generating one or more expansion phrases from the results set, the results set including at least one result;
an abbreviation detection component for selecting at least one of the generated expansion phrases based on one or more filter rules;
a ranking component for ranking the at least one selected expansion phrase; and
a database for associating the abbreviated term with the at least one selected expansion phrase.
10 . The system according to claim 9 , wherein the one or more expansion phrases are generated from at least one of a title of the result and a snippet of the result.
11 . The system according to claim 9 , wherein the ranking component ranks the at least one selected expansion phrase according to the frequency that the at least one selected expansion phrase is found within a query log.
12 . The system according to claim 9 , wherein the results set is received from a search engine.
13 . The system according to claim 12 , wherein the ranking component ranks the at least one selected expansion phrase according to the order the at least one selected expansion phrase is found within the results set from the search engine
14 . The system according to claim 9 , wherein the abbreviation detection component identifies the at least one selected expansion phrase by comparing the at least one abbreviated term to the one or more expansion phrases.
15 . The system according to claim 14 , wherein the abbreviation detection component compares the at least one abbreviated term by identifying letters within the one or more expansion phrases that are found in the at least one abbreviated term.
16 . One or more computer-readable media having computer-usable instructions stored thereon for performing a method for creating a database of expansion phrases for abbreviated terms, the method comprising:
receiving a results set corresponding to an abbreviated term, the results set comprising at least one result;
generating one or more expansion phrases from the results set;
selecting at least one of the generated expansion phrases based on one or more filter rules;
associating the abbreviated term with the at least one selected expansion phrase.
17 . The computer readable media according to claim 16 , further comprising ranking the at least one selected expansion phrase.
18 . The computer readable media according to claim 17 , wherein the results set is received from a search engine.
19 . The computer readable media according to claim 18 , further comprising ranking the at least one selected expansion phrase according to the order the at least one selected expansion phrase is found within the results set from the search engine.
20 . The computer readable media according to claim 18 , wherein the one or more expansion phrases are generated from at least one of a title of the result and a snippet of the result.