User-generated contents (UGC) represent an important source of information for
governments, companies, political candidates and consumers. However, most of the Natural …

This paper presents the general architecture of Curupira, a general-purpose robust parser
for Brazilian Portuguese (BP). As a former part of a grammar and style checker, Curupira …

Discourse markers are words and expressions (such as: firstly, then, for example, because,
as a result, likewise, in comparison, in contrast) that explicitly state the relational structure of …

Based on Cross-document Structure Theory (CST), we investigate the problem of finding
related sentences from multiple documents on the same topic. We test some lexical similarity …

This paper presents a new approach to quantify temporal novelties in Social Networks and,
as a consequence, to identify changing points driven by the occurrence of new real-world …

Although it has been always thought that Word Sense Disambiguation (WSD) can be useful
for Machine Translation, only recently efforts have been made towards integrating both tasks …

Descreve-se, neste artigo, a criação de um parser discursivo multidocumento automático
para textos escritos em português brasileiro, seguindo-se a teoria discursiva Cross …

Text classification is an important task of Artificial Intelligence. Normally, this task uses large
textual datasets whose representation is feasible because of normalization and selection …

Os avanços tecnológicos e científicos ocorridos nas últimas décadas têm proporcionado o
desenvolvimento de métodos cada vez mais eficientes para o armazenamento e …

Neste trabalho é descrita uma proposta metodológica para a construçao de taxonomias de
tópicos em um domınio de conhecimento. A proposta vem sendo desenvolvida de forma …