Mathematician by the Autonomous University of Madrid, and master's degree in Advanced Mathematics and Mathematical Engineering by the Polytechnic University of Catalonia.
Passionate about technology
Lifelong learner
Abstract: Word embeddings have recently become a fundamental tool of Natural Language Processing, with application to tasks like machine translation or image annotation. The high-dimensional space defined by these embeddings is typically explored and exploited through distance-based operations. In this paper we work on the problem of finding words related between them in a text embedding. This relationship can be of different kind, we focus in semantic relations like synonymy and antonym. We explore the idea of using the distance between norms instead of, like other authors has done before, the vector that units them. We present different norms, some of them well known in the literature and others no so widely used and also we introduce a new one and its theoretical mathematical framework. We also give an explanation of why them work properly or not and compare their performance on the two most used embeddings, GloVe and Word2Vec.
Relevant Coursework: Codes and Cryptography, Discrete and Algorithmic Geometry, Graph Theory, Estadística para la Gestión Empresarial (from MESIO, Máster universitario en Estadística e Investigación Operativa).
2015-2016: Universitat Autònoma de Barcelona (UAB).
2016-2017: Universitat Politècnica de Catalunya (UPC).
Apart from discovering new technologies, I play guitar almost every day and do Brazilian Jiu-Jitsu as much as I can.
Also, I spend part of my free time learning new mathematical concepts, trying new programming languages and reading, programming and implementing Artificial Intelligence algorithms.