Negation scope in portuguese: taxonomy, systematization and implementation

• Grant number: 23/01892-4
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: September 01, 2023
• End date: August 31, 2027
• Field of knowledge: Linguistics, Literature and Arts - Linguistics
• Principal Investigator: Oto Araújo Vale
• Grantee: Isaac Souza de Miranda Junior
• Host Institution: Centro de Educação e Ciências Humanas (CECH). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Company: Universidade de São Paulo (USP). Centro de Inovação da USP (INOVA)
• Associated research grant: 19/07665-4 - Center for Artificial Intelligence, AP.eScience.CPE

Abstract

Automatic detection of negation clues in an utterance and the elements that are modified by them, its scope, has become extremely relevant for Natural Language Processing (NLP). This importance has been demonstrated specifically in clinical health corpus (JIMÉNEZ-ZAFRA et. al, 2020, p,190). Concerning Portuguese, there are still a fell works on this subject: usually, the negation processing is made due to another activity that requires this type of detection (SAIAS et al, 2015; SAIAS et al, 2018; ANCHIÊTA, 2018; ALMEIDA NETO et al, 2021; OLIVEIRA et al, 2022, among others). Thus, this project aims to develop a linguistic-computational method capable of automatically identifying the negation scope in Portuguese sentences through dependency rules using the Universal Dependencies methodology (UNIVERSAL DEPENDENCIES, 2021), a morphosyntactic annotation. For this, it is intended to annotate the elements that indicate negation in the Porttinari corpus (PARDO et al, 2021) so that will serve as a language model for the UDPipe parser (STRAKA et al, 2016, STRAKA 2018). Finally, the automatic analysis of the parser will be used by the method so that, based on a set of rules, it can identify the scope negation through the syntax of the utterances. (AU)