1,722,529 research outputs found
An SVM Ensamble Approach to Detect Irony and Stereotype Spreaders on Twitter
Full text linkThe problem we address in this work is classifying whether a Twitter user has spread Irony and Stereotype or not. We used a text vectorization layer to generate Bag-Of-Words sequences. Then such sequences are passed to three different text classifiers (Decision Tree, Convolutional Neural Network, Naive Bayes). Our final classifier is an SVM. To test and validate our approach we used the dataset provided for the author profiling task organized by PAN@CLEF 2022. Our team (missino) submitted the predictions on the provided test set to participate at the shared task. Over several cross fold validation our approach was able to reach a maximum binary accuracy on the best validation split equal to 0.9474. On the test set provided for the shared task our model is able to reach an accuracy of 0.9389
La possidenza borghese in Transpadana. Silvestro Camerini
No full textThe book analyses the relationships over the time among actors, human environment and natural environment in Transpadana, through a case study concerning the history of a great private land property asset (unpublished archive documents)
Development problems and perspectives in Pakistan Barani Areas
No full textPatterns and development perspectives of the "barani" (rainfed) lands of Pakistan are discusse
La commassazione fondiaria in Pakistan,
No full textViene presentato il processo di commassazione/ricomposizione fondiaria in atto nel Punjab pakistan
Special Issue: Selected papers from the AIxIA 2023 Workshops
No full textThe 2023 edition of the AIxIA Conference, held in Rome, brought together a large number of researchers and practitioners to discuss the most recent and important advancements in Artificial Intelligence (AI). The conference featured 19 workshops, organized by 77 experts, attracting 248 submissions and resulting in 16 proceedings. This special issue presents extended versions of selected papers initially showcased at these workshops. Each paper underwent rigorous review and represents a diverse array of topics, reflecting the multifaceted nature of the Italian AI community. The topics covered include ethical foundations to symbiotic AI, symbolic knowledge extraction from black-box models, creative influence prediction using graph theory, AI approaches to multidimensional poverty prediction, an assessment of AI-based supports for informal caregivers, deep learning-based EEG denoising, AI-assisted board-game-based learning, large language models for assessment and feedback in higher education, geometric reasoning in the Traveling Salesperson Problem, defeasible reasoning in weighted knowledge bases, and conditional computation in neural networks. These contributions demonstrate the innovative and interdisciplinary research within the AI community, offering valuable insights and advancing the field
Rings for privacy: An architecture for large scale privacy-preserving data mining
Full text linkThis article proposes a new architecture for privacy-preserving data mining based on Multi Party Computation (MPC) and secure sums. While traditional MPC approaches rely on a small number of aggregation peers replacing a centralized trusted entity, the current study puts forth a distributed solution that involves all data sources in the aggregation process, with the help of a single server for storing intermediate results. A large-scale scenario is examined and the possibility that data become inaccessible during the aggregation process is considered, a possibility that traditional schemes often neglect. Here, it is explicitly examined, as it might be provoked by intermittent network connectivity or sudden user departures. For increasing system reliability, data sources are organized in multiple sets, called rings, which independently work on the aggregation process. Two different protocol schemes are proposed and their failure probability, i.e., the probability that the data mining output cannot guarantee the desired level of accuracy, is analytically modeled. The privacy degree, the communication cost and the computational complexity that the schemes exhibit are also characterized. Finally, the new protocols are applied to some specific use cases, demonstrating their feasibility and attractiveness
"Il territorio e l'ambiente. Monselice. Un profilo geografico."
No full textThe article focuses on the territorial analysis of Monselice, a medium size village in Padova province. Over the time, elements from natural environment have interacted with elements from human environment in order to design different territorial results
Deep bidirectional transformers for Italian question answering
No full textDeep learning continues to achieve state-of-the-art results in several NLP tasks, such as Question Answering (QA). Unfortunately, the requirements of neural QA systems are very strict in the size of the involved training datasets. Recent works show that the application of Automatic Machine Translation is an enabling factor for the acquisition of large scale QA training sets in resource poor languages such as Italian. In this work, we show how these resources can be used to train a state-of-the-art deep architecture, based on effective techniques recently proposed within the Bidirectional Encoder Representations from Transformers (BERT) paradigm
Adversarial training for few-shot text classification
No full textIn recent years, Deep Learning methods have become very popular in classification tasks for Natural Language Processing (NLP); this is mainly due to their ability to reach high performances by relying on very simple input representations, i.e., raw tokens. One of the drawbacks of deep architectures is the large amount of annotated data required for an effective training. Usually, in Machine Learning this problem is mitigated by the usage of semi-supervised methods or, more recently, by using Transfer Learning, in the context of deep architectures. One recent promising method to enable semi-supervised learning in deep architectures has been formalized within Semi-Supervised Generative Adversarial Networks (SS-GANs) in the context of Computer Vision. In this paper, we adopt the SS-GAN framework to enable semi-supervised learning in the context of NLP. We demonstrate how an SS-GAN can boost the performances of simple architectures when operating in expressive low-dimensional embeddings; these are derived by combining the unsupervised approximation of linguistic Reproducing Kernel Hilbert Spaces and the so-called Universal Sentence Encoders. We experimentally evaluate the proposed approach over a semantic classification task, i.e., Question Classification, by considering different sizes of training material and different numbers of target classes. By applying such adversarial schema to a simple Multi-Layer Perceptron, a classifier trained over a subset derived from 1% of the original training material achieves 92% of accuracy. Moreover, when considering a complex classification schema, e.g., involving 50 classes, the proposed method outperforms state-of-the-art alternatives such as BERT
- …
