Computational approaches to Portuguese: introduction to the special issue

The computational processing of PortugueseApproximately 250 million people speak the Portuguese language.It is one of the most spoken languages on the planet, being the official language in 10 regions of the world: Brazil, Portugal, Cape Verde, Angola, Guinea-Bissau, Mozambique, São Tomé and Príncipe, Equatorial Guinea, East Timor and Macau.The provision of computational infrastructure and services to support speakers of Portuguese is therefore of obvious importance.Computational processing of Portuguese began in the 1990s and has increased over the past three decades.Over this time, work on Portuguese has involved several scientific paradigms in the area of Natural Language Processing (NLP), such as symbolic approaches, statistical modeling and, more recently, neural learning, producing valuable theoretical contributions to the field as a whole as well as many resources, tools and applications for Portuguese.Although an international conference on the computational processing of Portuguese (PROPOR, for PROcessing of PORtuguese) has been held annually since 1993 (among many other relevant publication venues 1 ), we believe that at this time,