1 code implementation • Findings (EMNLP) 2021 • Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, Roberto Navigli
Multilingual Named Entity Recognition (NER) is a key intermediate task which is needed in many areas of NLP.
no code implementations • 19 Apr 2024 • Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella, Riccardo Marin, Emanuele Rodolà
We build upon the recent relative representations framework and adapt it for Visual RL.
1 code implementation • NeurIPS 2023 • Valentino Maiorca, Luca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, Emanuele Rodolà
While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible.
no code implementations • 2 Oct 2023 • Irene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, Emanuele Rodolà
It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases.
3 code implementations • 17 May 2023 • Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, Emanuele Rodolà
We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference.
1 code implementation • 15 Mar 2023 • Valeria Ruscio, Valentino Maiorca, Fabrizio Silvestri
We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics.
1 code implementation • 1 Mar 2023 • Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications.
no code implementations • 30 Sep 2022 • Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, Emanuele Rodolà
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations.
1 code implementation • 20 Sep 2022 • Giovanni Trappolini, Valentino Maiorca, Silvio Severino, Emanuele Rodolà, Fabrizio Silvestri, Gabriele Tolomei
In this work, we focus on a specific, white-box attack to GNN-based link prediction models, where a malicious node aims to appear in the list of recommended nodes for a given target victim.
1 code implementation • 8 Jun 2022 • Donato Crisostomi, Simone Antonelli, Valentino Maiorca, Luca Moschella, Riccardo Marin, Emanuele Rodolà
In this work, we tackle the problem of few-shot graph classification, showing that equipping a simple distance metric learning baseline with a state-of-the-art graph embedder allows to obtain competitive results on the task. While the simplicity of the architecture is enough to outperform more complex ones, it also allows straightforward additions.