Orthographical variant detection apparatus and orthographical variant detection method

1. An orthographical variant detection apparatus comprising:

a term extraction unit that extracts terms from document data;

a similarity computation unit that computes an edit distance of an arbitrary pair of the extracted terms based on the number of times of operations for editing one of the pair to match the other of the pair, the edit distance of a character type replacing operation being set to be shorter than respective edit distances of other operations, and computes a similarity of the pair based on the edit distance;

an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates; and

a group classification unit that groups the orthographical variant candidates based on a character string commonly included in the pair of terms as the orthographical variant candidates.

2. An orthographical variant detection apparatus comprising:

a term extraction unit that extracts terms from document data;

a similarity computation unit that performs operations including a character type replacing operation on an arbitrary pair of the extracted terms, computes an edit distance based on the number of times of the operations, the edit distance of the character type replacing operation being set to be shorter than respective edit distances of other operations, and computes a similarity based on the edit distance;

an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates;

a group classification unit that groups the orthogonal variant candidates based on a character string commonly included in the pair of terms as the orthogonal variant candidates; and

an orthogonal variant type determination unit that determines a type of an orthogonal variant of the pair of terms as the orthogonal variant candidate, based on a difference between the pair of terms.

3. A method for controlling an orthographical variant detection apparatus including a term extraction unit that extracts terms from document data, a similarity computation unit that computes an edit distance of an arbitrary pair of the extracted terms based on the number of times of operations for editing one of the pair to match the other of the pair, and computes a similarity of the pair based on the edit distance, an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates, and a group classification unit that groups the orthographical variant candidates based on a character string commonly included in the pair of terms as the orthographical variant candidates, the method comprising:

extracting, by the term extraction unit, the terms from the document data;

computing, by the similarity computation unit, the edit distance of the arbitrary pair of the extracted terms based on the number of times of operations for editing one of the pair to match the other of the pair, the edit distance of a character type replacing operation being set to be shorter than respective edit distances of other operations, and computing the similarity of the pair based on the edit distance;

determining, by the orthographical variant candidate determination unit, based on the similarity, whether or not the pair of terms are the orthographical variant candidates; and

grouping, by the group classification unit, the orthographical variant candidates based on the character string commonly included in the pair of terms as the orthographical variant candidates.

4. A method for controlling an orthographical variant detection apparatus including a term extraction unit that extracts terms from document data, a similarity computation unit that performs operations including a character type replacing operation on an arbitrary pair of the extracted terms, computes an edit distance based on the number of times of the operations, and computes a similarity based on the edit distance, an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates, a group classification unit that groups the orthogonal variant candidates based on a character string commonly included in the pair of terms as the orthogonal variant candidates, and an orthogonal variant type determination unit that determines a type of an orthogonal variant of the pair of terms as the orthogonal variant candidate, based on a difference between the pair of terms, the method comprising:

extracting, by the term extraction unit, the terms from the document data;

performing, by the similarity computation unit, the operations including the character type replacing operation on the arbitrary pair of the extracted terms, computing the edit distance based on the number of times of the operations, the edit distance of the character type replacing operation being set to be shorter than respective edit distances of other operations, and computing the similarity based on the edit distance;

determining, by the orthographical variant candidate determination unit, based on the similarity, whether the terms in the arbitrary pair of terms are the orthographical variant candidates;

grouping, by the group classification unit, the orthogonal variant candidates based on the character string commonly included in the pair of terms as the orthogonal variant candidates; and

determining, by the orthogonal variant type determination unit, the type of the orthogonal variant of the pair of terms as the orthogonal variant candidate, based on the difference between the pair of terms.