In this paper we report the first results of an annotation exercise of argument coercion phenomena performed on Italian texts. Our corpus consists of ca 4000 sentences from the PAROLE sottoinsieme corpus (Bindi et al. 2000) annotated with Selection and Coercion relations among verb-noun pairs formatted in XML according to the Generative Lexicon Mark-up Language (GLML) format (Pustejovsky et al., 2008). For the purposes of coercion annotation, we selected 26 Italian verbs that impose semantic typing on their arguments in either Subject, Direct Object or Complement position. Every sentence of the corpus contains information about corpus-derived typed selectional preferences for verbs in the targeted argument slots and is annotated with the source type for the noun arguments by two annotators plus a judge. An overall agreement of 0.87 kappa indicates that the annotation methodology is reliable. A qualitative analysis of the results allows us to outline some suggestions for improvement of the task: 1) a different account of inherently polysemous nouns has to be devised and 2) a more comprehensive account of coercion mechanisms requires annotation of the deeper meaning dimensions that are targeted in coercion operations, such as those captured by Qualia relations.
Capturing Coercions in Texts: a First Annotation Exercise
JEZEK, ELISABETTA;
2010-01-01
Abstract
In this paper we report the first results of an annotation exercise of argument coercion phenomena performed on Italian texts. Our corpus consists of ca 4000 sentences from the PAROLE sottoinsieme corpus (Bindi et al. 2000) annotated with Selection and Coercion relations among verb-noun pairs formatted in XML according to the Generative Lexicon Mark-up Language (GLML) format (Pustejovsky et al., 2008). For the purposes of coercion annotation, we selected 26 Italian verbs that impose semantic typing on their arguments in either Subject, Direct Object or Complement position. Every sentence of the corpus contains information about corpus-derived typed selectional preferences for verbs in the targeted argument slots and is annotated with the source type for the noun arguments by two annotators plus a judge. An overall agreement of 0.87 kappa indicates that the annotation methodology is reliable. A qualitative analysis of the results allows us to outline some suggestions for improvement of the task: 1) a different account of inherently polysemous nouns has to be devised and 2) a more comprehensive account of coercion mechanisms requires annotation of the deeper meaning dimensions that are targeted in coercion operations, such as those captured by Qualia relations.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
