View source for 18540615. RELYING ON DISCOURSE TREES TO BUILD ONTOLOGIES simplified abstract (Oracle International Corporation)

=RELYING ON DISCOURSE TREES TO BUILD ONTOLOGIES=


==Organization Name==

[[:Category:Oracle International Corporation|Oracle International Corporation]]


[[Category:Oracle International Corporation]]

==Inventor(s)==

[[:Category:Boris Galitsky of San Jose CA (US)|Boris Galitsky of San Jose CA (US)]][[Category:Boris Galitsky of San Jose CA (US)]]

==RELYING ON DISCOURSE TREES TO BUILD ONTOLOGIES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18540615 titled 'RELYING ON DISCOURSE TREES TO BUILD ONTOLOGIES

==Simplified Explanation==

The present invention involves discourse trees, where a method includes generating a discourse tree, identifying a central entity associated with a rhetorical relation of elaboration, determining a subset of elementary discourse units associated with the central entity, forming generalized phrases from the subset, forming tuples from the generalized phrases, and updating the ontology with an entity from the identified tuple.

* Discourse trees are used to analyze text structures and relationships between entities.
* The method involves identifying central entities and their associated rhetorical relations.
* Generalized phrases are formed from subsets of elementary discourse units.
* Tuples, which are ordered sets of words, are created from the generalized phrases.
* The ontology is updated with entities identified in the tuples.

== Potential Applications ==
The technology could be applied in:
* Text analysis and summarization tools
* Information retrieval systems
* Natural language processing applications

== Problems Solved ==
The technology helps in:
* Identifying central entities in texts
* Analyzing rhetorical relations in discourse
* Generating structured representations of text

== Benefits ==
The technology offers benefits such as:
* Improved text understanding and analysis
* Enhanced information retrieval capabilities
* Efficient summarization of large texts

== Potential Commercial Applications ==
The technology could be commercially applied in:
* Content management systems
* Search engines
* Educational tools

== Possible Prior Art ==
One possible prior art is the use of discourse analysis in linguistics and natural language processing research.

=== Unanswered Questions ===

=== How does the technology handle ambiguous central entities in discourse trees? ===
The technology may use context clues or additional algorithms to disambiguate central entities in discourse trees.

=== Can the technology be applied to multiple languages or is it limited to a specific language? ===
The technology may be adaptable to multiple languages through translation and language-specific rule sets.


==Original Abstract Submitted==

Systems, devices, and methods of the present invention involve discourse trees. In an example, a method involves generating a discourse tree. The method includes identifying, from the discourse tree, a central entity that is associated with a rhetorical relation of type elaboration and corresponds to a topic node that identifies a central entity of the text. The method includes determining a subset of elementary discourse units of the discourse tree that are associated with the central entity. The method includes forming generalized phrases from the subset of elementary discourse units. The method includes forming tuples from the generalized phrases, where a tuple is an ordered set of words in normal form. The method involves responsive to successfully converting an elementary discourse unit associated with an identified tuple into a logical representation, updating the ontology with an entity from the identified tuple.



[[Category:G06F40/295]]
[[Category:G06F40/35]]
[[Category:G06N5/04]]