Language Graph
The Language Graph is a linguistic knowledge base containing millions of concepts and over 100 million facts in the form of relations and annotations. It is used extensively by the linguistic algorithms to predict the senses of words, generate paraphrases, etc.
It contains almost all common words, many common multi-word expressions (e.g., nuclear reactor), and millions of named entities (proper nouns or adjectives). The named entities were mined from popular sources such as Wikipedia, MusicBrainz, etc. Where a sense was obtained from an external reference, that information is available and can be used by an application to establish a mapping between the Idilia sense and the matching Wikipedia page (for example).
The Language Graph service exposes the semantic relationships contained in the Language Graph. Both a machine interface and a visual browser are available.
Concepts
The following documents explain the concepts behind the Language Graph and its content.- Understanding the Language Graph: Provides an overview of the content and relationships contained in the Language Graph.
- Link Types: The nodes in the Language Graph are linked together by many different types of links to form several different types of relationships. This document explains them.
- Sense Annotations: In addition to links, the Graph contains several properties for the fine senses. These can be used by applications when transforming, generalizing, or classifying text.
- Mapping External Entities to the Language Graph: Shows how the Language Graph nodes can be mapped to those in other sources and vice-versa.
Getting Started
- Create an account on this web site or login: Login
- Create a project: Create Project
- Follow the example of your choice: Ruby
- Check out the visual browser: Browser
- Check out the API: kb/query and the Query Language
