| Method, device and system for part-of-speech disambiguation - Patent 6182028 (5594 words) |
 | Step 3 is the disambiguation step, in which all part-of-speech ambiguities in the sequence of ambiguously tagged text tokens are resolved by the disambiguator (110) as specified by the disambiguation knowledge database (111), thus resulting in a sequence of unambiguously tagged text tokens (112). |
| Text tokens with locally predicted tags 404 is an output of the local-context tagger and is one of the three input streams to the discriminator. |
| For example, if the local-context disambiguation algorithm was bigram-based stochastic disambiguation, these probabilities would be the conditional probabilities of each tag in the tag set of the current text token when preceded by a tag in the tag set of the previous text token, as determined by corpus analysis. |
Feeds |
Contact