Main Page
From Inpho Wiki
This wiki page will help you understand more about our project, as well as find detailed tutorials on how to use our interface, as an editor/collaborator or as a user.
Contents |
What is InPhO?
At the Indiana Philosophy Ontology (InPhO) Project, we are working to create a dynamic computational ontology for the discipline of philosophy. This knowledge representation is currently being developed primarily to serve the metadata needs of the Stanford Encyclopedia of Philosophy (SEP), although it may have a wide array of other uses.
The SEP is a peer-managed, open-access, dynamic reference work, with new entries constantly being published and old entries asynchronously edited. This creates a serious challenge: how can the SEP's metadata (cross-references, tables of contents, search keywords) be efficiently updated to reflect the changing content? Our approach to the problem is to combine statistical co-occurrence methods with expert feedback to create a dynamic semantic representation of the items described in the SEP's articles.
The InPhO contains categories for persons, documents, organizations, and, most importantly, philosophical ideas. The "person" ontology currently contains a great deal of biographical information about philosophers, and we are working on populating our "document" ontology with a full array of citation information. However, our taxonomy of philosophical ideas is the most useful area of the ontology for addressing the SEP's metadata needs. This taxonomy is generated by first using co-occurrence statistics to produce ranked candidate lists of hypernym and hyponym candidates for each idea term, which are then passed to SEP authors for evaluation. With the authors' feedback in hand--which gives us expert judgments of the relative similarity and generality of terms in the SEP--we can use answer set programming techniques to construct an taxonomy classifying these ideas according to their location in the "intellectual space" of the discipline.
Three Stage Method
The InPhO is a dynamic ontology constructed in a 3-step iterative process, described fully in our JCDL 2007 and FLAIRS 2008 papers. In short:
- A small, hand-built formal ontology was created using the subject-area structure of the Stanford Encyclopedia of Philosophy (SEP) and other resources to identify major topics and sub-topics in the domain of philosophical ideas.
- Statistical methods are run over the entries in the SEP to identify likely relationships among terms.
- Feedback from experts knowledgeable in philosophy is used to assess the results of step 2. This feedback is then stored as statements in first-order predicate logic, and then passed to a logic program we have designed to classify ideas in optimal locations for reachability to all other ideas deemed highly-related by experts. The finished product of this inference task is then viewable on the InPhO Taxonomy.
FAQs
Tutorials
We have created some step-by-step tutorials for editors and users:
- Navigating the Taxonomy
- Editing the Thinker Interface (requires login)
- Editing the Taxonomy (requires login)
Contact Us
Not only is the ontology dynamic, but so is our website and wiki! If you have any questions or concerns, please email inpho@indiana.edu. We will return with an answer ASAP. Thank you!
