Child-friendly search and automatic summarization

Interested in data science? Join us at our meetup in Meppel!

Program

18:00 - 18:30 Pizzas, drinks, networking
18:30 - 19:00 Child-friendly access to age-specific content - Thijs Westerveld (Thijs Westerveld)
19:00 - 19:30 Automatic summarization of online discussions (Suzan Verberne)
19:30 - 21:00 More drinks & networking

Abstracts and bio's can be found below.

Child-friendly access to age-specific content - Thijs Westerveld

abstract

WizeNoze is an Amsterdam based start-up that develops technology to make the Internet a more suitable place for children. The amount of online information that is targeted at children is currently small and the content that does exist is hard to find. In the main web search engines, this information gets overpowered by the plethora of information that is available for adults. Moreover, the information that is aimed at children often targets them as one homogeneous group, failing to differentiate between children of different ages and comprehension levels.
WizeNoze provides a child-friendly technology platform that increases the amount of content available to children, that improves the access to this information, and that targets each child at their own comprehension level.
In this talk we focus on our classification technology that given a text, determines the comprehension level required to understand it. This classifier needs to work with a highly heterogeneous set of training data with a mix of fine-grained and coarser labels that sometimes cover overlapping comprehension level ranges. We will showcase two applications in which we use the classification technology: the editing tool that helps authors to simplify their texts and the search engine to access our collection of content for children.

bio

Thijs Westerveld is an Information retrieval specialist with an interest in both scientific and practical work. As Chief Science Officer at WizeNoze, he is responsible for identifying, inventing and assessing algorithms to solve key technical questions to give customers access to the latest state of the art in kids technology. Thijs holds a PhD in Computer Science from the University of Twente and he has over 15 years experience in various areas of information retrieval, both in academic and industry settings.

Automatic summarization of online discussions - Suzan Verberne

abstract

In this talk I will present the DISCOSUMO project: Automatic Summarization of Discussion Forum threads. Discussion forums on the web come in many flavors, each covering its own topic and having its own community. The user-generated content on web forums is a valuable source for information. In the case of question answering forums such as StackOverflow and Quora, the opening post is a question and the responses are answers to that question. In these forums, the best answer may be selected by the forum community through voting. On the other hand, in discussion forums where opinions and experiences are shared, there is generally no such thing as `the best answer'. Moreover, discussion threads on a single topic can easily comprise dozens or hundreds of individual posts, which makes it difficult to find the relevant information in the thread, especially when the forum is accessed on a mobile device. In the DISCOSUMO project we address this challenge. I will show some of the results that we have obtained in the past year.

bio

Suzan Verberne is a researcher and teacher at Radboud University in Nijmegen. She obtained her PhD in 2010 on the topic of Question Answering and has since been working on the edge between text analysis and information retrieval. She has been involved in projects involving a large number of application domains: from art history to knowledge workers to patient communities. Her recent work centers around text mining from online content. She collaborates with TNO, the Dutch publisher Sanoma and non-profit organizations such as kanker.nl
http://sverberne.ruhosting.nl/