1. Overview

Semantic Assistants support users in content retrieval, analysis, and development, by offering context-sensitive NLP services directly integrated with common desktop applications (word processors, email clients, Web browsers, ...), web information systems (wikis, portals) and mobile applications (based on Android). They are implemented through an open service-oriented architecture, using Semantic Web ontologies and W3C Web Services.

Semantic Assistants Overview

1.1. Info Sheets

For the impatient, we have a few info sheets available:

The Semantic Computing course (SOEN 6211) is offered at Concordia University, providing graduate students with a unique opportunity to study research and development of novel semantic software systems. The course is taught by Prof. René Witte and supported by team members from the Semantic Software Lab. Students from other universities in Québec can register for this course through CREPUQ.

This course provide an introduction to selected topics from Semantic Computing, including text mining, tagging and tag analysis, recommender systems, RDF and linked data, semantic desktops and semantic wikis.

Within this project, we investigated semantic support, included ontologies, linked data, and text mining, for genozymes for bioproducts and bioprocesses development.
Through the selection of appropriate technologies and their combination in a coherent system that brings measurable improvements to the users, we develop a semantic infrastructure in support of genomics-based lignocellulose research.

In the next Winter Term (2010/11) I will offer, for the first time, a graduate-level research course on Semantic Computing (SOEN 691B) at the Department of Computer Science and Software Engineering. This course will provide an introduction to selected topics from Semantic Computing.

For those interested in performing NLP on source code, in particular Javadoc comments, we just released a Doclet at the NLP Frameworks workshop last week.

Its main feature is that it creates an XML corpus from Java source code that is optimised for processing in an NLP Framework (GATE in our case, but it should work for any framework that takes XML as input).

In the Semantic Assistants project, we investigate how to support users in content retrieval, analysis, and development, by offering context-sensitive NLP services directly integrated with common desktop applications (word processors, email clients, Web browsers, ...), web information systems (wikis, portals) and mobile applications (based on Android). They are implemented through an open service-oriented architecture, using Semantic Web ontologies and W3C Web Services.

The growing number of publicly available information sources makes it impossible for individuals to keep track of all the various opinions on one topic. The goal of our fuzzy believer project is to extract and analyze statements of opinion from newspaper articles.

Beliefs are modeled using a fuzzy-theoretic approach applied after NLP-based information extraction. A fuzzy believer models a human agent, deciding what statements to believe or reject based on different, configurable strategies.