How do children acquire their native language? How can this human ability be reproduced in machines? These fascinating questions have motivated my research so far.

My work is highly interdisciplinary. It lies in the intersection of Machine Learning, Natural Language Processing and Linguistics. My goal has been to develop computational systems that learn to understand and speak natural languages from multimodal data, inspired in the way children learn their native language. Ongoing research projects focus on the modeling of different linguistic phenomena in natural conversations by integrating a large set of multimodal cues, such as audio, video, text and neurophysiological data.