Idiap has a new opening for an Internship position in Natural Language Processing on DNN-based coreference models

Idiap has a new opening for an Internship position in Natural Language Processing on DNN-based coreference models

Co-reference is the relation between words or phrases in a text that refer to the same entity. DNNs have been successfully applied to a variety of NLP tasks, but for coreference resolution such approaches have shown limited improvement and a suitable model remains to be found. The goal of this internship is to go beyond classifiers that decide whether a pair of phrases is co-referent or not, and instead learn to represent, in the output layer, each of the entities of a text. In collaboration with a PhD student and a postdoc, the model will be applied to document-level machine translation. The work will thus relate to the EU SUMMA and SNSF MODERN projects.

Applications are invited for a 6-month internship at the Master level in the field of natural language processing with neural networks, in the NLP group of the Idiap Research Institute.

The goal of this internship is to explore new data structures that would enable a better modeling of co-reference by using deep neural networks (DNNs).

The applicants should have a background in natural language processing, machine learning, or computer science. They should have demonstrable programming skills in at least one language such as Perl, Python, Java or C/C++. Previous experience with coreference or anaphora resolution would be a plus. Good command of English is mandatory and knowledge of another European language such as French, Spanish, or German would be appreciated.

The screening of the applications will start on January 15, 2017, and will continue until the position is filled. The preferred starting time is in spring 2017. The appointment is for 6 months, with a gross internship salary of 2000 CHF per month.

To apply for this position, click on the following link:Internship position in Natural Language Processing on DNN-based coreference models