The paper reports on the design and construction of a multi-layered corpus of Italian, annotated at the syntactic and lexico-semantic levels, whose development is supported by dedicated software augmented with an intelligent interface. The issue of evaluating this type of resource is also addressed

Resumen:The system for semantic evaluation VENSES (Venice Semantic Evaluation System) is organized as a pipeline of two subsystems: the first is a reduced version of GETARUN, our system for Text Understanding. The output of the system is a flat list of head-dependent structures (HDS) with Grammatical Relations (GRs) and Semantic Roles (SRs) labels. The evaluation system is made up of two main modules: the first is a sequence of linguistic rule-based subcalls; the second is a quantitatively based measurement of input structures. VENSES measures semantic similarity which may range from identical linguistic items, to synonymous or just morphologically derivable. Both modules go through General Consistency checks which are targeted to high level semantic attributes like presence of modality, negation, and opacity operators, temporal and spatial location checks. Results in cws, accuracy and precision are homogenoues for both training and test corpus and fare higher than 60%.

No abstract

Abstract. We argue in this paper that in order to properly capture opinion and sentiment expressed in texts or dialogs any system needs a deep linguistic processing approach. As in other systems, we used ontology matching and concept search, based on standard lexical resources, but a natural language understanding system is still required to spot fundamental and pervasive linguistic phenomena. We implemented these additions to VENSES system and the results of the evaluation are compared to those reported in the state-of-the-art systems in sentiment analysis and opinion mining. We also provide a critical review of the current benchmark datasets as we realized that very often sentiment and opinion is not properly modeled.

Shakespeare's Sonnets have been studied by literary critics for centuries after their publication. However, only recently studies made on the basis of computational analyses and quantitative evaluations have started to appear and they are not many. In our exploration of the Sonnets we have used the output of SPARSAR which allows a full-fledged linguistic analysis which is structured at three macro levels, a Phonetic Relational Level where phonetic and phonological features are highlighted; a Poetic Relational Level that accounts for a poetic devices, i.e. rhyming and metrical structure; and a Syntactic-Semantic Relational Level that shows semantic and pragmatic relations in the poem. In a previous paper we discussed how colours may be used appropriately to account for the overall underlying mood and attitude expressed in the poem, whether directed to sadness or to happiness. This has been done following traditional approaches which assume that the underlying feeling of a poem is strictly related to the sounds conveyed by the words besides/beyond their meaning. In that study we used part of Shakespeare's Sonnets. We have now extended the analysis to the whole collection of 154 sonnets, gathering further evidence of the colour-sound-mood relation. We have also extended the semantic-pragmatic analysis to verify hypotheses put forward by other quantitative computationally-based analysis and compare that with our own. In this case, the aim is trying to discover what features of a poem characterize most popular sonnets.