Authors: Brunello, Andrea | Croce, Danilo
Article Type: Editorial
Abstract: The 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. Show more
Keywords: Artificial intelligence, ethical AI, explainable AI, AI for healthcare, AI in education, formal methods, deep learning, geometric reasoning
DOI: 10.3233/IA-240071
Citation: Intelligenza Artificiale, vol. 18, no. 1, pp. 5-8, 2024
Authors: Croce, Danilo | Castellucci, Giuseppe | Bastianelli, Emanuele
Article Type: Research Article
Abstract: The use of complex grammatical features in statistical language learning assumes the availability of large scale training data and good quality parsers, especially for languages different from English. In this paper, we show how good quality FrameNet Semantic Role Labeling systems can be obtained without relying on full syntactic parsing, by backing off to surface grammatical representations and structured learning. In line with this approach, the ioB Annotation Based Engine for srL (BABEL) has been implemented as a flexible system for Semantic Role Labeling based on a Structured Support Vector Machine learning framework. While the underlying learning paradigm allows employing …BABEL when no syntactic parser is available, its accuracy is in line with state-of-the-art systems for English. BABEL is among the best performing Semantic Role Labeling systems also for Italian, as recently evaluated in the role labeling task of the Frame Labeling over Italian Texts at the Evalita 2011 competition. Moreover, the same learning framework is applied to effectively acquire surface grammatical information, achieving state-of-the-art results also with respect to the Part-of-speech tagging task of the Evalita 2009 competition. Finally, BABEL can POS tag more than 1,500 word per second while the SRL module can process about 35 sentences per second, thus making its use straightforward in Web scale applications. Show more
Keywords: Structured support vector machine, Semantic role labeling, Part-of-speech Tagging
DOI: 10.3233/IA-120035
Citation: Intelligenza Artificiale, vol. 6, no. 2, pp. 163-176, 2012
Authors: Croce, Danilo | Castellucci, Giuseppe | Basili, Roberto
Article Type: Research Article
Abstract: In 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. Show more
Keywords: Semi-supervised learning, generative adversarial network, kernel-based embedding spaces, universal sentence encoding
DOI: 10.3233/IA-200051
Citation: Intelligenza Artificiale, vol. 14, no. 2, pp. 201-214, 2020
Authors: Croce, Danilo | Filice, Simone | Basili, Roberto
Article Type: Research Article
Abstract: Expressive but complex kernel functions, such as Sequence or Tree kernels, are usually underemployed in NLP tasks as for their significant computational cost in both learning and classification stages. Recently, the Nyström methodology for data embedding has been proposed as a viable solution to scalability problems. It improves scalability of learning processes acting over highly structured data, by mapping data into low-dimensional compact linear representations of kernel spaces. In this paper, a stratification of the model corresponding to the embedding space is proposed as a further highly flexible optimization. Nyström embedding spaces of increasing sizes are combined in an efficient …ensemble strategy: upper layers, providing higher dimensional representations, are invoked on input instances only when the adoption of smaller (i.e., less expressive) embeddings provides uncertain outcomes. Experimental results using different models of such an uncertainty show that state-of-the-art accuracy on three semantic inference tasks can be obtained even when one order of magnitude fewer kernel computations is carried out. Show more
Keywords: Nyström method, scalability, kernel methods, structured language learning
DOI: 10.3233/IA-170109
Citation: Intelligenza Artificiale, vol. 11, no. 2, pp. 93-116, 2017
Authors: Croce, Danilo | Zelenanska, Alexandra | Basili, Roberto
Article Type: Research Article
Abstract: The recent breakthroughs in the field of deep learning led to state-of-the-art results in several NLP tasks, such as Question Answering (QA). Unfortunately, the requirements of such neural QA systems are very strict due to the size of the involved training datasets. In cross-linguistic settings these requirements are not satisfied as training datasets for QA over non-English texts are often not available. This represents the major barrier for a wide-spread adoption of neural QA methods in NLP applications. In this paper, the acquisition of a large scale dataset for an open-domain factoid question answering system in Italian is discussed. It …is obtained by automatic translation and linguistic elicitation of an existing English dataset, i.e. the SQuAD question-answer pair corpus. Even though the quality of the resulting corpus for Italian might not be completely satisfying, our work allowed to generate more than 60 thousand question-answer pairs. In the paper the impact of this resource on the QA process over the Italian Wikipedia is studied, according to different training conditions and architectural constraints. A comparative evaluation against the English version, in line with standards in the SQuAD literature, is carried out. The outcomes show that the results achievable for Italian are below the state-of-the-art for English, but the ability of learning not to respond (i.e. the adoption of techniques for detecting question whose answers are simply not available, i.e. EMPTY set of answers) allows the system to pursue reasonable levels of precision. This make it already usable within realistic application scenarios. Finally, an error analysis is presented that suggests possible future research directions on still critical but highly beneficial enhancements, in view of concrete QA applications in Italian. Show more
Keywords: Question answering in Italian, deep learning, recurrent neural network with attention
DOI: 10.3233/IA-190018
Citation: Intelligenza Artificiale, vol. 13, no. 1, pp. 49-61, 2019
Authors: Hromei, Claudiu D. | Croce, Danilo | Basili, Roberto
Article Type: Research Article
Abstract: Situated natural language interactions between humans and robots are strictly necessary for complex applications: communication here implies the reference to the environment shared between a user and the robot. This paper proposes a transformer-based architecture that supports the integration of spatial information (as logical representation) about a semantic map of the environment and the input utterances. The generated interpretation is a logical form of the command that makes references to the state of the world through a single end-to-end process, stimulated at each interaction by an explicit linguistic description of the environment. In this specific work, the end-to-end capability of …the targeted transformer is studied in light of its multilingual applications where the robot can be queried in different natural languages. The obtained experimental results confirm the applicability of transformers to grounded human-robotic interaction, with benefits in terms of both portability of the approach across domains and effectiveness in terms of reachable accuracy. Moreover, language-specific processing chains are shown to be preferable to large-scale multilingual models for their better trade-off between accuracy and complexity. Overall, the proposed architecture outperforms previous approaches and paves the way for sustainable multilingual architectures. Show more
Keywords: Grounded semantic role labeling, human-robot interaction, end to end sequence to sequence architectures, robotics and perception, italian automatic interpretation
DOI: 10.3233/IA-230012
Citation: Intelligenza Artificiale, vol. 17, no. 2, pp. 173-191, 2023