Publications de Diego Matteo Antognini

Unsupervised Term Extraction for Highly Technical Domains

Term extraction is an information extraction task at the root of knowledge discovery platforms. Developing term extractors that are able to generalize across very diverse and potentially highly technical domains is challenging, as annotations for domains r ...

2022

Positive and Negative Critiquing for VAE-based Recommenders

Boi Faltings, Diego Matteo Antognini

Providing explanations for recommended items allows users to refine the recommendations by critiquing parts of the explanations. As a result of revisiting critiquing from the perspective of multimodal generative models, recent work has proposed M&Ms-VAE, w ...

2022

Active Learning for Imbalanced Civil Infrastructure Data

Diego Matteo Antognini, Adelmo Cristiano Innocenza Malossi, Ioana Giurgiu

Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections to support the pr ...

2022

Textual Explanations and Critiques in Recommendation Systems

Diego Matteo Antognini

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual data. Moreover, ...

EPFL2022

Assistive Recipe Editing through Critiquing

Boi Faltings, Diego Matteo Antognini

There has recently been growing interest in the automatic generation of cooking recipes that satisfy some form of dietary restrictions, thanks in part to the availability of online recipe data. Prior studies have used pre-trained language models, or relied ...

2022

Interlock-Free Multi-Aspect Rationalization for Text Classification

Diego Matteo Antognini

Explanation is important for text classification tasks. One prevalent type of explanation is rationales, which are text snippets of input text that suffice to yield the prediction and are meaningful to humans. A lot of research on rationalization has been ...

2022

Multi-Step Critiquing User Interface for Recommender Systems

Boi Faltings, Diana Andreea Petrescu, Diego Matteo Antognini

Recommendations with personalized explanations have been shown to increase user trust and perceived quality and help users make better decisions. Moreover, such explanations allow users to provide feedback by critiquing them. Several algorithms for recomme ...

ASSOC COMPUTING MACHINERY2021

Interacting with Explanations through Critiquing

Boi Faltings, Claudiu-Cristian Musat, Diego Matteo Antognini

Using personalized explanations to support recommendations has been shown to increase trust and perceived quality. However, to actually obtain better recommendations, there needs to be a means for users to modify the recommendation criteria by interacting ...

2021

Recommending Burgers based on Pizza Preferences: Addressing Data Sparsity with a Product of Experts

Claudiu-Cristian Musat, Diego Matteo Antognini, Martin Milenkoski

In this paper, we describe a method to tackle data sparsity and create recommendations in domains with limited knowledge about user preferences. We expand the variational autoencoder collaborative filtering from a single-domain to a multi-domain setting. T ...

2021

Momentum-based Gradient Methods in Multi-Objective Recommendation

Boi Faltings, Claudiu-Cristian Musat, Diego Matteo Antognini

Multi-objective gradient methods are becoming the standard for solving multi-objective problems. Among others, they show promising results in developing multi-objective recommender systems with both correlated and conflicting objectives. Classic multi-grad ...

2021