Port4NooJ v3.0: Integrated Linguistic Resources for Portuguese NLP

Port4NooJ v3.0: Integrated Linguistic Resources for Portuguese NLP Cristina Mota1, Paula Carvalho1,2, Anabela Barreiro1 1L2F / INESC-ID Lisboa, 2Universidade Europeia | Laureate International Universites cmota@ist.utl.pt, {pcc,abarreiro}@inesc-id.pt Abstract This paper introduces Port4NooJ v3.0, the latest version of the Portuguese module for NooJ, highlights its main features, and details its three main new components: (i) a lexicon-grammar based dictionary of 5,177 human intransitive adjectives, and a set of local grammars that use the distributional properties of those adjectives for paraphrasing (ii) a polarity dictionary with 9,031 entries for sentiment analysis, and (iii) a set of priority dictionaries and local grammars for named entity recognition. These new components were derived and/or adapted from publicly available resources. The Port4NooJ v3.0 resource is innovative in terms of the specificity of the linguistic knowledge it incorporates. The dictionary is bilingual Portuguese-English, and the semantico-syntactic information assigned to each entry validates the linguistic relation between the terms in both languages. These characteristics, which cannot be found in any other public resource for Portuguese, make it a valuable resource for translation and paraphrasing. The paper presents the current statistics and describes the different complementary and synergic components and integration efforts. Keywords: paraphrasing, sentiment analysis, named entity recognition 1. Introduction NooJ (Silberztein, 2015; Silberztein, 2016) is a multi- lingual linguistic environment to develop linguistic re- sources, and process written texts. Currently, NooJ in- cludes over 20 language modules. Port4NooJ is the Por- tuguese language module of NooJ, and it includes linguis- tic resources, such as: (i) a large coverage dictionary with English transfers1; (ii) rules to formalize and document Portuguese inflectional and derivational descriptions, and (iii) local grammars, namely morphological, disambigua- tion, semantico-syntactic, morphological grammars to in- flect and generate multiword expressions, and translation grammars. Port4NooJ different components interact among them and are used to process texts. Several processing func- tions can be performed with these resources, among others, part of speech annotation, semantic analysis, named entity recognition, translation and paraphrasing. The module can be downloaded from the NooJ website2. In this paper we present the Port4NooJ v3.0, focusing in the description of its three main new components: (i) a lexicon- grammar based dictionary of human intransitive adjectives, and a set of local grammars that use the distributional prop- erties of those adjectives for paraphrasing, (ii) a polarity dictionary for sentiment analysis, and (iii) linguistic re- sources for named entity recognition. There is no other public resource for Portuguese that incorporates such a va- riety of linguistic knowledge. This research work was developed in the scope of the eS- PERTo3 project. The main objective of this project is twofold: (i) develop a context-sensitive and linguistically 1Due to its bilingual characteristics, this dictionary can be used in translation. The addition of transfers for other languages are easily implemented, since they already exist in the Logos system and are publicly available in OpenLogos. 2http://www.nooj-association.org/ 3In Portuguese, "esperto" means "smart", but here it is also an acronym for "System of Paraphrasing for Editing and Revision of Text" ("Sistema de Parafraseamento para Edição …

Content truncated to 500 words