| 摘要 |
A natural language processing apparatus (10) includes a result acquisition unit (11) that acquires a plurality of analysis results indicating parts of speech of morphemes contained in one or more common sentences, the analysis results obtained by analyzing the one or more common sentences using a plurality of types of morphological analyzers A1, A2 and A3, a pattern acquisition unit (12) that detects a common segmentation point in the plurality of analysis results, extracts one or more parts of speech corresponding to a character string segmented at the common segmentation point from each of the analysis results, and acquires a set of the extracted one or more parts of speech as a part-of-speech differing pattern, a storage unit (13) that stores the acquired part-of-speech differing pattern together with the number of appearances of the part-of-speech differing pattern, and a candidate specifying unit (14) that extracts the part-of-speech differing pattern with the number of appearances being equal to or less than a predetermined threshold from the storage unit (13) and specifies the character string corresponding to the extracted part-of-speech differing pattern as a character string containing a candidate for an unknown word. |
