Here is a quote from Oracle Docs.
AUTO_LEXER type to index columns that contain documents of different languages. It performs language identification, word segmentation, document analysis, part-of-speech tagging, and stemming. The
AUTO_LEXER also enables customization of these components. Although parts-of-speech information that is generated by the
AUTO_LEXER is not exposed for your use,
AUTO_LEXER uses it for context-sensitive or tagged stemming."
My question is, why is it not exposed? This feature would be extremely helpful. Is it exposed in Oracle Data Mining? Will it be exposed in the future? This decision by Oracle still leaves folks with no choice but to look elsewhere when it comes to doing some basic text mining.
Usually features are not exposed because they are not considered production ready in a release. While they have been fully tested in the "closed" environment where they are in use, they may not have been fully tested in an open, uncontrolled environment. It is likely that this feature will be exposed in a future version.