Tagging and Labelling Portuguese Modal Verbs

Abstract

Abstract. We present in this paper an experiment in automatically tagging a set of Portuguese modal verbs with modal information. Modality is the expression of the speaker's (or the subject's) attitude towards the content of the sentences and may be marked with lexical clues such as verbs, adverbs, adjectives, but also by mood and tense. Here we focus exclusively on 9 verbal clues that are frequent in Portuguese and that may have more than one modal meaning. We use as our gold data set a corpus of 160.000 tokens manually annotated, according to a modality annotation scheme for Portuguese. We apply a machine learning approach to predict the modal meaning of a verb in context. This modality tagger takes into consideration all the features available from the parsed data (pos, syntactic and semantic). The results show that the tagger improved the baseline for all verbs, and reached macro-average F-measures between 35 and 81% depending on the modal verb and on the modal value.

Tagging modality in Oceanic languages of Melanesia

“…These distinctions are notoriously difficult to tag, with coarse-grained ontologies yielding better results than more fine-grained ones (Rubinstein et al, 2013). Most approaches focus on modal auxiliaries such as must, and modal adverbs such as probably (Cui and Chi, 2013;Quaresma et al, 2014). In the languages of our project, however, modal auxiliaries and adverbs are rare, and do not play the same role in expressing modality as they do in many European languages.…”

“…These distinctions are notoriously difficult to tag, with coarse-grained ontologies yielding better results than more fine-grained ones (Rubinstein et al, 2013). Most approaches focus on modal auxiliaries such as must, and modal adverbs such as probably (Cui and Chi, 2013;Quaresma et al, 2014).…”

Detección de operadores modales

“…El análisis de los OM también se ha llevado a cabo a través de estudios de corpus (Hendrickx et al, 2012;Nissim et al, 2013;Ghia et al, 2016). En este tipo de estudios la metodología se basa en la anotación manual de corpus, que sirve para incrementar los registros de OM y como recurso para desarrollar propuestas computacionales de detección y anotación de estas partículas (Baker et al, 2010;Rubinstein et al, 2013;Quaresma et al, 2014). Estos registros pueden ser utilizados de forma directa o bien como fuente para crear sistemas de detección basados en reglas (Saurí et al, 2005(Saurí et al, , 2006Soni et al, 2014;Lee et al, 2015).…”

Glossolalia em games: um estudo de caso no videogame NieR:Automata

“…Em relação aos fonemas fricativos [ʃ] (pronunciado como o "x" de "xícara") e [ʒ] (pronunciado como a letra "j' em "jogo"), estes são transcritos, respectivamente, como "sh" e "j". A escolha de "sh" ao invés de "x" para o fonema [ʃ] se deu por conta da letra "x" aparecer com pouca frequência tanto no idioma português [Quaresma 2008] quanto em outros idiomas que utilizam o alfabeto latino [Grigas e Juškevičienė 2018].…”