Verb Clustering for Brazilian Portuguese

Abstract

Abstract. Levin-style classes which capture the shared syntax and semantics of verbs have proven useful for many Natural Language Processing (NLP) tasks and applications. However, lexical resources which provide information about such classes are only available for a handful of worlds languages. Because manual development of such resources is extremely time consuming and cannot reliably capture domain variation in classification, methods for automatic induction of verb classes from texts have gained popularity. However, to date such methods have been applied to English and a handful of other, mainly resource-rich languages. In this paper, we apply the methods to Brazilian Portuguese -a language for which no VerbNet or automatic class induction work exists yet. Since Levinstyle classification is said to have a strong cross-linguistic component, we use unsupervised clustering techniques similar to those developed for English without language-specific feature engineering. This yields interesting results which line up well with those obtained for other languages, demonstrating the crosslinguistic nature of this type of classification. However, we also discover and discuss issues which require specific consideration when aiming to optimise the performance of verb clustering for Brazilian Portuguese and other less-resourced languages.

Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation

“…State-of-the-Art A direct comparison of previous state-of-the-art classification scores available for FR (Sun et al, 2010) and PT (Scarton et al, 2014) on the same test data exemplifies the extent of improvement achieved by our transfer model. F-1 scores improve from 0.55 to 0.75 for FR and from 0.43 to 0.73 for PT.…”

“…Test Data The development of an automatic verb classification approach requires an initial gold standard (Sun et al, 2010): these have been developed for FR (Sun et al, 2010), PT (Scarton et al, 2014), IT, PL, HR, and FI (Majewska et al, 2017). They were created using the methodology of Sun et al (2010), based on the EN gold standard of Sun et al (2008) which contains 17 fine-grained Levin classes with 12 member verbs each.…”

Investigating the cross-lingual translatability of VerbNet-style classification

“…The classification chosen for translation was the VerbNet data used by Sun et al (2008) and previously translated from English into French (Sun et al 2010) and Brazilian Portuguese (Scarton et al 2014). This resource includes 17 fine-grained classes sampled from different parts of the VerbNet taxonomy, with 12 member verbs each (e.g., '9.1 PUT' class: bury, place, install, put, mount, deposit, position, set, situate, immerse, insert, stash).…”

“…Others have been created (semi-)automatically, using already existing resources and aiming to reduce the time-expense involved, e.g., for Brazilian Portuguese (Scarton and Aluısio 2012), French (Pradet et al 2014), and Croatian (Mikelić Preradović and Boras 2013). Also fully automatic methods have been used, e.g., for French (Sun et al 2010) and Brazilian Portuguese (Scarton et al 2014). However, this work has been limited to a small number of languages.…”

“…Manual development of such taxonomies using Levin's methodology is extremely time consuming. A cost-effective alternative that has been used to support both the manual development of VerbNets (e.g., Pala and Horák 2008) as well as creation of gold standards for (semi-)automatic verb classification (Sun et al 2010;Scarton et al 2014) is translation of VerbNet classes from English to other languages.…”