Italy

In this paper we present a novel mechanism to get explanations that allow to better understand network predictions when dealing with sequential data. Specifically, we adopt memory-based networks — Differential Neural Computers — to exploit their capability of storing data in memory and reusing it for inference. By tracking both the memory access at prediction time, and the information stored by the network at each step of the input sequence, we can retrieve the most relevant input steps associated to each prediction. We validate our approach (1) on a modified T-maze, which is a non-Markovian discrete control task evaluating an algorithm’s ability to correlate events far apart in history, and (2) on the Story Cloze Test, which is a commonsense reasoning framework for evaluating story understanding that requires a system to choose the correct ending to a four-sentence story. Our results show that we are able to explain agent’s decisions in (1) and to reconstruct the most relevant sentences used by the network to select the story ending in (2). Additionally, we show not only that by removing those sentences the network prediction changes, but also that the same are sufficient to reproduce the inference.

AIxIA 2021

Explainable Inference on Sequential Data via Memory-Tracking

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

EACL 2023

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

technical paper

[![](https://assets.underline.io/uploads/markdown_image/1/image/9a88ae95fbde06e80f4bcf6d4f7d133a.png)](https://certificateaixia.paperform.co/)
The certificate will be provided by December 17. 
In case you need it urgently please contact: francesca.gasparini@unimib.it. 

 

The 20th International Conference of the Italian Association for Artificial Intelligence (**AIxIA 2021**) is organized by AIxIA (Associazione Italiana per l’Intelligenza Artificiale), which is a non-profit scientific society founded in 1988 and devoted to the promotion of Artificial Intelligence. The society aims to increase the public awareness of AI, encourage the teaching of it and promote research in the field.

 
 



**General Chair**

Stefania Bandini, University of Milano-Bicocca, Italyand RCAST - The University of Tokyo, Japan


**Program Chairs**

Viviana Mascardi, University of Genova, Italy; Matteo Palmonari, University of Milano-Bicocca, Italy; Giuseppe Vizzari, University of Milano-Bicocca, Italy

**Organizing Committee**

Francesca Gasparini, University of Milano-Bicocca, Italy (**Chair**); Stefano Ferilli, University of Bari, Italy; Marta Giltri, University of Milano-Bicocca, Italy; Daniela Briola, University of Insubria, Italy


**Publicity and Communication Committee**

Elisabetta Fersini, University of Milano-Bicocca, Italy (**Chair**); Angelo Ferrando, University of Genova, Italy; Francesca Alessandra Lisi, University of Bari, Italy; Giovanni Stilo, University of L'Aquila, Italy; Marco Viviani, University of Milano-Bicocca, Italy


**Workshop Chairs**

Gabriella Cortellessa, ISTC-CNR, Rome, Italy; Silvia Rossi, University of Naples Federico II, Italy; Fabio Stella, University of Milano-Bicocca, Italy


**PC Members**

Fulvio Mastrogiovanni, University of Genova, Italy; Roberto Basili, University of Rome Tor Vergata, Italy; Nicola Gatti, Polytechnic University of Milan, Italy; Stefano Bistarelli, University of Perugia, Italy; Piero Poccianti, Consorzio Operativo Gruppo MPS, Italy; Francesco Scarcello, University of Calabria, Italy; Flavio S. Correa Da Silva, University of São Paulo, Brazil; Elena Cabrio, Université Côte d'Azur, CNRS, Inria, I3S, France; Antonio Lieto, University of Turin, Italy; Diego Calvanese, Free University of Bozen-Bolzano, Italy; Alessio Micheli, University of Pisa, Italy; Francesca A. Lisi University of Bari Aldo Moro, Italy; Mauro Vallati, University of Huddersfield, United Kingdom; Bernardo Magnini, Fondazione Bruno Kessler (FBK), Italy; Luigia C. Aiello, Sapienza University of Rome, Italy; Rafael H. Bordini, Pontifical Catholic University of Rio Grande do Sul, Brazil; Chiara Ghidini, Fondazione Bruno Kessler (FBK), Italy; Federico Bergenti, University of Parma, Italy; Francesco Ricca, University of Calabria, Italy; Andrea Burattin, Technical University of Denmark, Denmark; Angelo Oddi, ISTC-CNR, Italian National Research Council, Italy; Farshad Badie, Aalborg University, Denmark; Emanuel Sallinger, University of Oxford, United Kingdom; Marin Lujak, University Rey Juan Carlos, Spain; Giancarlo Fortino, University of Calabria, Italy; Salvatore Gaglio, University of Palermo, Italy; Johannes K. Fichte, TU Dresden, Germany; Matteo Baldoni, University of Turin, Italy; Fabrizio Riguzzi, Univeristy of Ferrara, Italy; Ivana Dusparic, Trinity College Dublin, Ireland; Serena Villata, CNRS - Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis, France; Paolo Rosso, Technical University of Valencia, Spain; Ana L. C. Bazzan, Federal University of Rio Grande do Sul, Brazil; Gianluigi Greco, University of Calabria, Italy; Stefano Cagnoni, University of Parma, Italy; Gian Luca Pozzato, University of Turin, Italy; Salvatore Ruggieri, University of Turin, Italy; Claudio Di Ciccio, Sapienza University of Rome, Italy; Eloisa Vargiu, Cetaqua, Water Technology Center, Spain; Marco Maratea, University of Genova, Italy; Andrea Roli, University of Bologna, Italy; Viviana Patti, University of Turin, Italy; Stefania Costantini, University of L'Aquila, Italy; Antonius Weinzierl, Vienna University of Technology, Austria; Silvia Rossi, University of Naples Federico II, Italy; Giovanni Semeraro, University of Bari, Italy; Luciano Serafini, Fondazione Bruno Kessler (FBK), Italy; Laura Giordano, University of Eastern Piedmont, Italy; Ernesto Jimenez-Ruiz, City, University of London, United Kingdom; Marco Gavanelli, University of Ferrara, Italy; Federico Chesani, University of Bologna, Italy

Please register with AIxIA to be able to enter the conference on Underline.io. If you have already registered, please login to Underline.io to be able to see full conference content. In case you do not have an Underline account, please create one. Thank you

Please login to your Underline account

The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021) is organized by AIxIA (Associazione Italiana per l’Intelligenza Artificiale), which is a non-profit scientific society founded in 1988 and devoted to the promotion of Artificial Intelligence. The society aims to increase the public awareness of AI, encourage the teaching of it and promote research in the field.

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the "black box" nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness. The basic idea of this paper is to exploit the human prior knowledge of the features' importance for a specific task, in order to coherently aid the phase of the model's fitting. This sort of "weighted" AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.

Logic Constraints to Feature Importances

Pruned Graph Neural Network for Short Story

Recent advances in natural language processing have improved our understanding of what kind of linguistic knowledge is encoded in modern word representations. For example, methods for testing the ability to extract syntax trees from a language model architecture were developed by Hewitt and Manning (2019)—they project word vectors into Euclidean subspace in such a way that the corresponding squared Euclidean distance approximates the tree distance between words in the syntax tree. This work proposes a method for assessing whether embedding word representations in hyperbolic space can better reflect the graph structure of syntax trees. We show that the tree distance between words in a syntax tree can be approximated well by the hyperbolic distance between corresponding word vectors.

Hyperbolic Embedding for Finding Syntax in BERT

The computation and memory needed for Convolutional Neural Network (CNN) inference can be reduced by pruning weights from the trained network. Pruning is guided by a pruning saliency, which heuristically approximates the change in the loss function associated with the removal of specific weights. Many pruning signals have been proposed, but the performance of each heuristic depends on the particular trained network. This leaves the data scientist with a difficult choice. When using any one saliency metric for the entire pruning process, we run the risk of the metric assumptions being invalidated, leading to poor decisions being made by the metric. Ideally we could combine the best aspects of different saliency metrics. However, despite an extensive literature review, we are unable to find any prior work on composing different saliency metrics. The chief difficulty lies in combining the numerical output of different saliency metrics, which are not directly comparable. We propose a method to compose several primitive pruning saliencies, to exploit the cases where each saliency measure does well. Our experiments show that the composition of saliencies avoids many poor pruning choices identified by individual saliencies. In most cases our method finds better selections than even the best individual pruning saliency.

Improving Existing Channel Saliency Metrics with Structural Information

Machine Learning Techniques, properly combined with Data Structures, have resulted in Learned Static Indexes, innovative and powerful tools that speed-up Binary Search, with the use of additional space with respect to the table being searched into. Such space is devoted to the ML model. Although in their infancy, they are methodologically and practically important, due to the pervasiveness of Sorted Table Search procedures. In modern applications, model space is a key factor and, in fact, a major open question concerning this area is to assess to what extent one can enjoy the speed-up of Learned Indexes while using constant or nearly constant space models. We address it here by (a) introducing two new models, i.e., denoted {\bf KO-BFS} and {\bf SY-RMI}, respectively; (b) by systematically exploring, for the first time, the time-space trade-offs of a hierarchy of existing models, i.e., the ones in {\bf SOSD}, together with the new ones. We document a novel and rather complex time-space trade-off picture, which is very informative for users. We experimentally show that the {\bf KO-BFS }can speed up Interpolation Search and Uniform Binary Search in constant space. For other versions of Binary Search, our second model, together with the bi-criteria {\bf PGM} index, can achieve a speed-up with a model space of 0.05% more than the one taken by the table, being competitive in terms of time-space trade-off with existing proposals. The {\bf SY-RMI} and the bi-criteria {\bf PGM} complement each other quite well across the various levels of the internal memory hierarchy. Finally, our findings are of interest to designers, since they highlight the need for further studies regarding the time-space relation in Learned Indexes.

Learned Sorted Table Search and Static Indexes in Small Model Space

The broad availability of machine learning (ML) libraries and frameworks makes the rapid prototyping of ML models a relatively easy task to achieve. However, the quality of prototypes is challenged by their reproducibility. Reproducing an ML experiment typically entails repeating the whole process, from data collection to model building, other than multiple optimization steps that must be carefully tracked. In this paper, we define a comprehensive taxonomy to characterize tools for ML experiment tracking and review some of the most popular solutions under the lens of the taxonomy. The taxonomy and related recommendations may help data scientists to more easily orient themselves and make an informed choice when selecting appropriate tools to shape the workflow of their ML experiments.

A Taxonomy of Tools for Reproducible Machine Learning Experiments

Siamese Networks with Transfer Learning for Change Detection in Sentinel-2 Images

Virtual Power Plants (VPP) are one of the main components of future smart electrical grids, connecting and integrating several types of energy sources, loads and storage devices. A typical VPP is a large industrial plant with high (partially shiftable) electric and thermal loads, renewable energy generators and electric and thermal storages. Optimizing the use and the cost of energy could lead to a significant economic impact. This work proposes a VPP Energy Management System (EMS), based on a two-step optimization model that decides the minimum-cost energy balance at each point in time considering the following data: electrical load, photovoltaic production, electricity costs, upper and lower limits for generating units and storage units. The first (day-ahead) step models the prediction uncertainty using a robust approach defining scenarios to optimize the load demand shift and to estimate the cost. The second step is an online optimization algorithm, implemented within a simulator, that uses the optimal shifts produced by the previous step to minimize, for each timestamp, the real cost while fully covering the optimally shifted energy demand. The system is implemented and tested using real data and we provide analysis of results and comparison between real and estimated optimal costs.

Robust optimization models for local flexibility characterization of Virtual Power Plants

Knowledge-based neural pre-training for Intelligent Document Management

Artificial Intelligence solutions are empowering many fields of knowledge, including art. Indeed, the growing availability of large collections of digitized artworks, coupled with recent advances in Pattern Recognition and Computer Vision, offer new opportunities for researchers in these fields to help the art community with automatic and intelligent support tools. In this discussion paper, we outline some research directions that we are exploring to contribute to the challenge of understanding art with AI. Specifically, our current research is primarily concerned with visual link retrieval, artwork clustering, integrating new features based on contextual information encoded in a knowledge graph, and implementing these methods on social robots to provide new engaging user interfaces. The application of Information Technology to fine arts has countless applications, the most important of which concerns the preservation and fruition of our cultural heritage, which has been severely penalized, along with other sectors, by the ongoing COVID pandemic. On the other hand, the artistic domain poses entirely new challenges to the traditional ones, which, if addressed, can push the limits of current methods to achieve better semantic scene understanding.

Downloads

Next from AIxIA 2021

Logic Constraints to Feature Importances

Similar lecture

Multimodal Event Transformer for Image-guided Story Ending Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AIxIA 2021

Logic Constraints to Feature Importances

Similar lecture

Multimodal Event Transformer for Image-guided Story Ending Generation

Downloads