Fiche du document
21 septembre 2022
- handle: 10670/1.vjmkv8
- isbn: 978-3-031-15925-1
- hal: hal-03790582
- doi: 10.1007/978-3-031-15925-1_12
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-031-15925-1_12
Mots-clés
Multiword expression Dictionary for language processing Portuguese Brazilian Portuguese Adverb Lexical Database Lexicon-Grammar UnitexSujets proches
Language (New words, slang, etc.)Citer ce document
Izabela Meira Grein Müller et al., « Bootstrapping a Lexicon of Multiword Adverbs for Brazilian Portuguese », HAL-SHS : linguistique, ID : 10.1007/978-3-031-15925-1_12
Métriques
Partage / Export
Résumé
This paper describes a process for bootstrapping a computational lexicon of multiword adverbs for Brazilian Portuguese (PT-BR) from an already existing lexicon built for the European variety of the language (PT-PT). This ongoing work aims to identify, collect, and provide a syntactical description of multiword adverbs in PT-BR, in order to produce a comprehensive lexicon of multiword adverbs in Portuguese. First, we review existing resources for this part-of-speech, then we describe the method adopted for building this novel resource. Up to the present moment, approximately 700 new PT-BR multiword adverbs have been recorded in the lexicon, totaling nearly 2,300 entries. We assessed this new lexical resource against a sample of 1,000 sentences, taken from a publicly available corpus collected from Brazilian Portuguese journalistic texts. Results are promising, although there is still room for improvement, given that the F-measure only reached a suboptimal 0.66 mark. We estimate that another 2,100 PT-BR adverbs will enter the lexicon, totaling +4,000 multiword adverbs in Portuguese.