We create new connections through advanced research and technology in vision, text, machine learning, UX and ethnography.
Our multidisciplinary approach to AI allows us to tackle challenges from different perspectives and gives greater meaning to our work.
A novel framework for controlled NLG called 'Generation with Distributional Control', achieves great generality on the types of constraints that can be imposed and has a large potential to remedy the problem of bias in language models.
Papers and activities of NAVER LABS Europe at EACL 2021. NLG, scaling to larger context, cost of supervised data, controlling the output plus ASR at the AfricaNLP workshop.
Our Global BERT-based Transformer architecture fuses global and local information at every layer, resulting in a reading comprehension model that achieves a deeper understanding for long documents and enables flexibility for downstream tasks.