POeTiSA

POeTiSA is a long term project that aims at growing syntax-based resources and developing related tools and applications for Brazilian Portuguese language in order to achieve world state-of-the-art results in this area. On the resource side, we focus on the production of a large and comprehensive multi-genre corpus of Universal Dependencies-based part of speech and syntactically annotated texts. Regarding the tools, we aim to investigate recent neural and distributional-based methods for training robust parsing models for Portuguese. The project also envisions the production of applications on opinion mining and sentiment analysis tasks that may benefit from syntactic knowledge, as opinion summarization, helpfulness prediction, aspect identification, deception detection and emotion classification.