Showing posts from December, 2016

[Talk Summary 13] Concept Map Extraction from Textbooks

Shuting Wang, 5th year PhD student, from Computer Science department, Penn State University had the talk "Concept Map Extraction from Textbooks" on Dec 05, 2016. In the talk, she presented three parts of her work: extracting concept hierarchy from textbook, using prerequisite to extract concept maps from textbook, and using the concept maps for automatic assessment.

First of all, Shuting talked about how to extract concept hierarchy from textbook. In her work, she extracted important concepts in each book chapter using Wikipedia as a resource and then construct a concept hierarchy for that book. She presented the process to construct a concept hierarchy as follows:
Build a concept dictionary from Wikipedia entities related to the topic of the book.Select concept candidates in the concept dictionary based on title and content similarity between a section (subchapter) in the book and Wikipedia articles.Construct the concept hierarchy from the table of content order of the book w…

[Talk Summary 12] A/B Testing at Scale

Dr. Pavel Dmitriev, a Principal Data Scientist, from Microsoft's Analysis and Experimentation team had a talk about "A/B Testing at Scale" on Thursday, 2016/12/08. The talk was about the introduction of a controlled experiment, four real experiments that Microsoft had been running, and 5 challenges about testing at scale.

Dr. Pavel started the talk with a brief introduction of controlled experiments, aka A/B tests. A/B testing is a method of comparing two versions of a webpage or app against each other to determine which one performs better. A/B testing is also used to evaluate a new feature of an application. If the feature has an effect on users, the result will show the significant difference (p<0.05); the lack of different is called null hypothesis.

With the evolving product development process, Dr. Pavel presented the motivation for A/B testing. In classical software development, a product is usually designed, developed, tested and then released. However, in cust…

[Talk Summary 11] Explain and answer: Intelligent systems which can communicate about what they see

Dr. Marcus Rohrbach from University of California, Berkeley made a talk "Explain and answer: Intelligent systems which can communicate about what they see" on Friday, 2016//12/02. In the talk, Marcus presented the models which can answer questions but at the same time are modular and expose their semantic reasoning structure, and showed how to generate explanations given only image captions as training data.

To begin the talk, Marcus showed the motivation of how to make the computer able to talk to about the visual world. He introduced two components in a successful communication: (1) the ability to answer natural language questions about the visual world, and (2) the ability of the system to explain in natural language, allowing a human to trust and understand it. to deal with tasks such as visual question answering, he emphasized that it is important to integrate the representation of textual and visual information together.

 Marcus described the whole process of the system …