In the lab meeting this week, 15th of April, Anoop will give a demo on new features in Lensing Wikipedia Project. In the second half of the meeting, Anoop will talk about how to exploit Apache Spark for distributed computing. The meeting would be the same location at the usual time.
In the lab meeting this week, 8th of April, Ziqi Wang and Yulan Huang will talk about the glm-parser project to write a state of the art dependency parser using Python and Cython. They will talk about the design of the project, a brief look at the algorithms and the speed up they were able to obtain by the use of better algorithms, the use of Cython, etc. The project is hosted on github at:
Golnar is going to give a talk about Graph-based Semi-supervised learning in the lab meeting this week. The meeting is on Wednesday, 1st of April, at 1:30 pm.
Abstract:“Semi-supervised learning (SSL) brings the best of supervised and unsupervised learning together: it takes advantage of labelled data when available, while using information hidden in usually abundant unlabelled data.
Graph-based SSL has frequently beaten other SSL approaches in the past, and has been applied to many NLP applications: POS-tagging, dependency parsing, and semantic analysis to name a few. It encourages similar data points to take similar labels even if they appear far from each other in training data (ex. across sentences).
In this talk, I will cover the basics of Graph-based SSL such as graph construction, graph propagation, and inductive vs. transductive methods, while using POS-tagging as a running example task.”
In the lab meeting this week, Wed March 25th, Paulo Marques, our visiting researcher, will talk about his research proposal, titled “Brazilian research funding in dengue – 2000-2014”.
Abstract: The research proposal focuses on funding for science and technology in Brazil. The expectation is to bring to discussion the imperative of the search for data sources which would allow the first and necessary step to rethink public policies on the subject to be taken. Dispersed and fragmented data about research funding cause challenges to build solid public policies. In addition, a big number of funding agencies in Brazil brings the necessity of an appropriate coordination. Its main goal is to develop a methodology in order to explain the pattern of public funding of the research on dengue in Brazil from the Federal Official Gazette (FOG).
Bio: Paulo graduated in Information Technology (1992) and during almost 15 years he was in charge of my own business focused on IT infrastructure. In 2006 he began to work for one of the major health research and development institution in Brazil called Oswaldo Cruz Foundation. He is a post-graduated in Scientific and Technology Information in Health (2007); and has a Master in Public Health (2011). Nowadays he is a graduate student in Health Information and Communication; and he is doing part of his doctorate in Natlang Lab/SFU.
This Wednesday (18th of March), Dan Fass is going to give a talk on the OCC Model of Emotion Types. Lab meeting will be held in TASC1 9408 at 1:30pm. Here is the abstract of this talk:
Abstract: The OCC Model of emotion (Ortony et al, 1988) is one of the best-known theories of emotion and the most widely used emotion theory of its type computationally. The model consists of 22 categories of emotion (known as “emotion types”) that Ortony et al organized into a hierarchy. Steunebrink (2010) took a compositional view of the emotion types, resulting in a restructuring of the types into an inheritance hierarchy. In this talk, an alternative method is used to identify issues with certain OCC Model emotion types, and a solution is proposed for the issues identified. The solution is then related to Steunebrink’s work and other work in affective science, affective NLP, and affective computing.