No abstract

In this paper, we present design and construction of the first Italian corpus for automatic and semi-automatic text simplification. In line with current approaches, we propose a new annotation scheme specifically conceived to identify the typology of changes an original sentence undergoes when it is manually simplified. Such a scheme has been applied to two aligned Italian corpora, containing original texts with corresponding simplified versions, selected as representative of two different manual simplification strategies and addressing different target reader populations. Each corpus was annotated with the operations foreseen in the annotation scheme, covering different levels of linguistic description. Annotation results were analysed with the final aim of capturing peculiarities and differences of the different simplification strategies pursued in the two corpora.

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of linguistic annotation. We show that BERT is able to encode a wide range of linguistic characteristics, but it tends to lose this information when trained on specific downstream tasks. We also find that BERT's capacity to encode different kind of linguistic properties has a positive influence on its predictions: the more it stores readable linguistic information of a sentence, the higher will be its capacity of predicting the expected label assigned to that sentence.

In this paper, we present a crowdsourcingbased approach to model the human perception of sentence complexity. We collect a large corpus of sentences rated with judgments of complexity for two typologically-different languages, Italian and English. We test our approach in two experimental scenarios aimed to investigate the contribution of a wide set of lexical, morpho-syntactic and syntactic phenomena in predicting i) the degree of agreement among annotators independently from the assigned judgment and ii) the perception of sentence complexity.

In this paper we present PaCCSS-IT, a Parallel Corpus of Complex-Simple Sentences for ITalian. To build the resource we develop a new method for automatically acquiring a corpus of complex-simple paired sentences able to intercept structural transformations and particularly suitable for text simplification. The method requires a wide amount of texts that can be easily extracted from the web making it suitable also for less-resourced languages. We test it on the Italian language making available the biggest Italian corpus for automatic text simplification.

We study the influence of context on how humans evaluate the complexity of a sentence in English. We collect a new dataset of sentences, where each sentence is rated for perceived complexity within different contextual windows. We carry out an in-depth analysis to detect which linguistic features correlate more with complexity judgments and with the degree of agreement among annotators. We train several regression models, using either explicit linguistic features or contextualized word embeddings, to predict the mean complexity values assigned to sentences in the different contextual windows, as well as their standard deviation. Results show that models leveraging explicit features capturing morphosyntactic and syntactic phenomena perform always better, especially when they have access to features extracted from all contextual sentences.

We report the results of the SemEval 2022 Task 3, PreTENS, on evaluation the acceptability of simple sentences containing constructions whose two arguments are presupposed to be or not to be in an ordered taxonomic relation. The task featured two sub-tasks articulated as: (i) binary prediction task and (ii) regression task, predicting the acceptability in a continuous scale. The sentences were artificially generated in three languages (English, Italian and French). 21 systems, with 8 system papers were submitted for the task, all based on various types of fine-tuned transformer systems, often with ensemble methods and various data augmentation techniques. The best systems reached an F1-macro score of 94.49 (sub-task1) and a Spearman correlation coefficient of 0.80 (sub-task2), with interesting variations in specific constructions and/or languages.

In this paper we describe the early stage application of the Universal Dependencies to an Italian corpus from social media developed for shared tasks related to irony and stance detection. The development of this novel resource (TWITTIRÒ-UD) serves a twofold goal: it enriches the scenario of treebanks for social media and for Italian, and it paves the way for a more reliable extraction of a larger variety of morphological and syntactic features to be used by sentiment analysis tools. On the one hand, social media texts are especially hard to parse and the limited amount of resources for training and testing NLP tools further damages the situation. On the other hand, we thought that adding the Universal Dependencies format to the fine-grained annotation for irony, that was previously applied on TWITTIRÒ, might meaningfully help in the investigation of possible relationships between syntax and semantics of the uses of figurative language, irony in particular.