Related papers: Centering in Italian
This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of…
Responsive teaching is a highly effective strategy that promotes student learning. In math classrooms, teachers might "funnel" students towards a normative answer or "focus" students to reflect on their own thinking, deepening their…
The Steprans forcing notion arises as a quotient of Borel sets modulo the ideal of $\sigma$-continuity of a certain Borel not $\sigma$-continuous function. We give a characterization of this forcing in the language of trees and using this…
In a recent article, I showed that in several academic disciplines in Italy, professors display a paucity of last names that cannot be explained by unbiased, random, hiring processes. I suggested that this scarcity of last names could be…
From a diachronic corpus of Italian, we build consecutive vector spaces in time and use them to compare a term's cosine similarity to itself in different time spans. We assume that a drop in similarity might be related to the emergence of a…
We introduce the central Fubini-like numbers and polynomials using Rota approach. Several identities and properties are established as generating functions, recurrences, explicit formulas, parity, asymptotics and determinantal…
We present a factorized compositional distributional semantics model for the representation of transitive verb constructions. Our model first produces (subject, verb) and (verb, object) vector representations based on the similarity of the…
Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these models rely on word-order/syntactic or word…
The concept of a fully interlacing matrix of formal power series with real coefficients is introduced. This concept extends and strengthens that of an interlacing sequence of real-rooted polynomials with nonnegative coefficients, in the…
This paper examines demonstrative pronouns used as deictics to refer to the interpretation of one or more clauses. Although this usage is frowned upon in style manuals (for example Strunk and White (1959) state that ``This. The pronoun…
The representation of sentences is a very important task. It can be used as a way to exchange data inter-applications. One main characteristic, that a notation must have, is a minimal size and a representative form. This can reduce the…
A statistical physics study of punctuation effects on sentence lengths is presented for written texts: {\it Alice in wonderland} and {\it Through a looking glass}. The translation of the first text into esperanto is also considered as a…
Nominalization is a highly productive phenomena in most languages. The process of nominalization ejects a verb from its syntactic role into a nominal position. The original verb is often replaced by a semantically emptied support verb…
We test the hypothesis that the degree of grammaticalization of German prepositions correlates with their corpus-based contextual dispersion measured by word entropy. We find that there is indeed a moderate correlation for entropy, but a…
While multilingual language models can improve NLP performance on low-resource languages by leveraging higher-resource languages, they also reduce average performance on all languages (the 'curse of multilinguality'). Here we show another…
Italian master's thesis in Computer Science. It is an overview of the standard tecniques developed in the field of Proof Theory, ending with some results in the new field of Deep Inference, plus an original contribution trying to relate…
Intensive Care in-hospital mortality prediction has various clinical applications. Neural prediction models, especially when capitalising on clinical notes, have been put forward as improvement on currently existing models. However, to be…
It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label. In this paper, we focus on an overlooked…
Prompt-Tuning is an efficient method for adapting pre-trained language models to new tasks with minimal computational overhead by modifying prompt embeddings. In this work, we investigate how crucial the phenomenon of embedding collapse,…
Referring expression comprehension aims to localize objects identified by natural language descriptions. This is a challenging task as it requires understanding of both visual and language domains. One nature is that each object can be…