Our workshop on closely related languages and language varieties was mentioned in the German newspaper “Die Welt”. They talk about dialect identification with respect to immigration: 170317_Dialektanalyse_Welt_Hummel
Welcome to our new PostDoc Yves Scherrer
Efficient MCMC word alignment
We have published an article on efficient word alignment:
- Robert Östling and Jörg Tiedemann: Efficient Word Alignment with Markov Chain Monte Carlo. The Prague Bulletin of Mathematical Linguistics (PBML), Number 106, pp. 125–146
The software is available at github: efmaral
Workshop on Machine Translation for Finnish
BAULT organises a one-day workshop on machine translation for morphologically-rich languages and Finnish in particular. The event is free of charge (space limits may apply) and you are welcome to attend. Please, register here.
Shared Task: Cross-lingual Pronoun Prediction
We organise a shared task on cross-lingual pronoun prediction at the first conference on machine translation (WMT2016) in connection with ACL 2016 in Berlin. All information can be found at the following website. Make sure that you don’t miss the deadlines in case you’d like to participate! The training data is out already.
Important dates are:
- Release of training data: 2nd February 2016
- Test data released: 4th April 2016
- System submission deadline: 11th April 2016
- Paper submission deadline: 8th May 2016
- Notification of acceptance: 5th June 2016
- Camera-ready deadline: 22nd June 2016
Everyone can participate! You only need to build a classifier for the given tasks!
Workshop on Cross-Lingual NLP
The language technology group organises an international workshop on multilingual and cross-lingual NLP on Thursday, 11 February, 2016. The program and further information can be found at the workshop website. Check it out!