cmput391 Winter 2020 Homework #1

Learning Objectives

The Semantic Web is a visionary development aimed at having web sites provide structured data with associated machine-readable semantics. There is quite a lot of activity around this initiative, including the Linked Open Data movement. In this paradigm, data is modeled as a graph encoded in RDF (Resource ...

more ...

cmput391 Winter 2020 Homework #2

Learning Objectives

XML is a versatile markup language suitable for encoding almost any kind of data there is, from structured data (e.g., relations) to unstructured data (e.g., emails, books, etc.). XML is widely supported by commercial DBMSs out there and has found many applications outside the realm of ...

more ...





cmput696 Information Extraction & Knowledge Graphs

cmput696 is a project-based course where students will be exposed to methods for the creation and curation of knowledge graphs and some of their applications. There are no formal prerequisites, but students are expected to have basic familiarity with natural language processing, query languages, machine learning and embeddings.

Learning Objectives ...

more ...

cmput696 Readings


Overview

  • E. Hovy, R. Navigli, and S. P. Ponzetto. Collaboratively built semi-structured content and artificial intelligence: the story so far. Artif. Intell., 194:2–27, January 2013. doi:10.1016/j.artint.2012.10.002. [Bibtex]
more ...


Neural Fine-Grained Entity Type Classification

Neural Fine-grained Entity Type Classification is the task of assigning a fine-grained type (e.g., athlete or artist instead of just person) to an entity mentioned in text. Fine-grained types have been shown superior to the standard generic types for most NLP tasks, including information extraction which is our main ...

more ...