Towards a semantic classification of Spanish verbs based on subcategorisation information

Abstract

We present experiments aiming at an automatic classification of Spanish verbs into lexical semantic classes. We apply well-known techniques that have been developed for the English language to Spanish, proving that empirical methods can be re-used through languages without substantial changes in the methodology. Our results on subcategorisation acquisition compare favourably to the state of the art for English. For the verb classification task, we use a hierarchical clustering algorithm, and we compare the output clusters to a manually constructed classification.

Verb Clustering for Brazilian Portuguese

“…Portuguese falls behind English and French in performance. Yet, the best results for this language, obtained without any language specific feature engineering, are (in contrast to the earlier verb clustering experiment for Spanish [24]) well beyond the random baseline. This together with the fact that similar feature sets tend to obtain the highest and lowest results among the three languages is encouraging and also demonstrates the cross-linguistic potential of Levin's classification.…”

“…The prior works most related to ours are those by Ferrer [24] for Spanish and Sun et al [25] and Falk et al [26] for French. Ferrer applied a simple hierarchical clustering approach developed for English to Spanish, and evaluated it against a manual classification of Vazquez [34] which is similar in nature (but not identical) to that of Levin's.…”

“…[24][25][26]. Interestingly, the recent experiment performed by Sun et al demonstrates that it is possible to take an unsupervised clustering method developed for English [27] and apply it successfully to French [25], using French NLP tools for feature extraction, but without language specific feature engineering.…”

A Comparison of Selectional Preference Models for Automatic Verb Classification

“…We cluster German verbs using features capturing their valency or subcategorisation, following prior work (Schulte im Walde, 2000;Esteve Ferrer, 2004;Schulte im Walde, 2006;Sun et al, 2008;Li and Brew, 2008), and investigate the effect of adding information about verb argument preferences. SPs are represented by features capturing lexical information about the heads of arguments to the verbs; we restrict our focus here to nouns.…”

VerbNet.Br: construção semiautomática de um léxico verbal online e independente de domínio para o português do Brasil

“…É neste recurso que esta pesquisa é baseada, com vistas à criação de um recurso semelhante para o português, via a proposta de um método de criação que também é resultado da pesquisa. Além disso, foram apresentadas as extensões deste recurso em relação às classes básicas propostas por Levin (1993 (Ferrer, 2004;Sun and Korhonen, 2009;Sun et al, 2010;Sun et al, 2011) …”