Archive

Offspring from Reproduction Problems (invitation to discussion and announcement ACL presentation)

Despite clear methodological descriptions and making our code and data available, it is still difficult to make our research reproducible. We would like to invite the NLP community to join a discussion on reproducing results from NLP research. One of the main questions we want to address is how we can get a better understanding of our methods through systematic research. Please visit our website: http://wordpress.let.vupr.nl/reproducingnlpresearch/ to join our discussion group or share your experiences and ideas. …or come and talk to…

Read More

FBK Workshop “Perspectives on Events”

Since one of the goals of NewsReader is to extract information on events from large streams of news and build structured indexes for decision making in the financial and economical domain, it is crucial to define what an event is. Although the notion of event has long been central for both modeling the semantics of natural language as well as reasoning in goal-driven tasks in artificial intelligence, the research community has yet to achieve a consensus on what is an…

Read More

Knowledge Store Paper accepted at the 7th IEEE International Conference on Semantic Computing

The following paper, describing the design of the Knowledge Store for NewsReader, has been accepted as full regular paper at the 7th IEEE International Conference on Semantic Computing (ICSC), to be held in Irvine, CA, USA, September 16-18, 2013: Francesco Corcoglioniti, Marco Rospocher, Roldano Cattoni, Bernardo Magnini, Luciano Serafini – Interlinking Unstructured and Structured Knowledge in an Integrated Framework, In 7th IEEE International Conference on Semantic Computing (ICSC), Irvine, CA, USA, 2013.

Read More

Antske Fokkens to present at Annual Network Institute Event

Antske Fokkens will present at the Annual Network Institute Event on July 4. During this event, the different groups working together in the interdisciplinary Network Institute at VU University will come together to exchange their research ideas and results. Antske will describe her attempts at reproducing some research published by others in her field, using the original data. And guess how easy that was…  

Read More

NWR at OpeNER hackathon

Yesterday, several NWR team members participated in the Natural Language Processing, Text Mining and Big Data Hackathon organised by our colleagues from the OpeNER project. During this hackathon, some 50 participants (amongst others developers, linguists, designers and historians) got together to put current state-of-the-art language technology through a little stress test in some actual use cases. The app ideas that the different teams came up with varied from analysing hotel reviews and visualising the results in different ways, to mining…

Read More