Presentations

NewsReader at ISWC

With Semantic Web technology being a huge part of NewsReader, it is no wonder that we will showcase some of our technology at the 14th International Semantic Web Conference (ISWC) next week in Bethlehem, Pennsylvania. Here’s a roundup of the sessions in which NewsReader is involved. Sunday 11 October The third NLP&DBpedia workshop (location: RBC 91): This workshop combines the two main themes in NewsReader, namely Natural Language Processing and Semantic Web. NewsReader team member Marieke van Erp is a co-organiser of this workshop…

Read More

Computational Models of Narrative (CMN’14)

Last week the 2014 Workshop Computational Models of Narrative took place in Quebec City, Canada and Marieke was there to present and discuss ideas for shaping the NewsReader narratives. This year’s workshop had a special focus on Neuroscience, but really all sorts of domains got covered in the three day workshop. Whilst at first some of the topics seemed quite far from NewsReader (after all, it is rather unlikely that we will put people in fMRI scanners to measure their appreciation of…

Read More

NWR at LREC2014

We are happy to announce the presence of several NewsReader team members at LREC2014. They will give updates on NewsReader during the following sessions: May 26: 09:30 – 10:00: Antske Fokkens, Aitor Soroa, Zuhaitz Beloki, Niels Ockeloen, Piek Vossen, German Rigau and Willem Robert van Hage. NAF and GAF: Linking Linguistic Annotations (10th Joint ACL – ISO Workshop on Interoperable Semantic Annotation, Rima B)  [paper] [slides] May 27: 09:00 – 10:00: Piek Vossen – Keynote 3rd Workshop on Linked Data…

Read More

NewsReader at CLIN24

On Friday 17 January NWR team member Marieke van Erp presented work on entity recognition and disambiguation at CLIN24. This work is a collaboration with researchers from EURECOM and Università degli studi di Torino. Slides are available through slideshare. Evaluating Named Entity Recognition and Disambiguation in News and Tweets from Marieke van Erp

Read More

NWR Presence at ISWC 2013

Next week NWR will be represented at ISWC 2013 by Luciano Serafini, Willem Robert van Hage, Thomas Ploeger and Marieke van Erp. Your greatest chances of running into these NWR team members will be at the following sessions: On Monday: Marieke is co-organising the Linked Science workshop, which this year has a special focus on reproducibility, scientific investigations and experiments. Don’t miss out on Carole Goble‘s keynote there! On Monday afternoon Marieke and Willem are co-organising the DeRiVE 2013 workshop,…

Read More

NWR Paper Nominated for Best Paper at ACL

The paper “Offspring from Reproduction Problems: What Replication Failure Teaches Us” which was co-authored by NewsReader team members Antske Fokkens, Marieke van Erp and Piek Vossen was runner up for the best paper award at ACL 2013 last week. In the paper, difficulties in reproducibility of prior research tools and experiments are addressed. Many researchers have come across cases where they had wanted to reuse an approach described in a research paper but found out that it was very difficult…

Read More

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

NERD-ML 2nd in MSM2013 Concept Extraction Challenge

Together with Giuseppe Rizzo and Raphaël Troncy from EURECOM, NewsReader team member Marieke van Erp participated in the MSM2013 Concept Extraction Challenge with a system called NERD-ML. This system was developed  to identify and classify named entities in microposts (Tweets). Their system ranked 2nd in the challenge, only 0.01 points in F-score behind the best system. NERD-ML is built on top of the NERD framework developed at EURECOM that makes it possible to easily query different named entity extractors that are available on the web. With NERD-ML, this framework…

Read More