摘要 |
A tagging device for identifying parts-of-speech of text includes a first part-of-speech tagger that provides, at a first output, a part-of-speech tag for each term in the text and a set of specialized part-of-speech taggers, having an output coupled to a device output and also having an input. The set of specialized part-of-speech taggers provide a set of candidate part-of-speech tags for each term provided at the input to the set of specialized part-of-speech taggers. An exception handler, coupled to the first output provides, in response to each term in the text, a part-of-speech tag from the first output to the device output, unless the term in the text is included in an exception list, in which case the term is provided to the input of the set of specialized part-of-speech taggers. A voting procedure may be used to select a part-of-speech tag from the set of candidate part-of-speech tags produced by the specialised part-of-speech-taggers for terms on the exception list. |