Deep Learning | Gabriele Sarti

Deep Learning

Inseq: An Interpretability Toolkit for Sequence Generation Models

An open-source library to democratize access to model interpretability for sequence generation models

Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties

We investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features.

Characterizing Linguistic Complexity in Humans and Language Models

Presenting my work on studying different metrics of linguistic complexity and how they correlate with linguistic phenomena and learned representations in neural language models

Contrastive Language-Image Pre-training for the Italian Language

We present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-text pairs.

Contrastive Image-Text Pretraining for Italian

The first CLIP model pretrained on the Italian language.

That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models

This paper investigates the relationship between two complementary perspectives in the human assessment of sentence complexity and how they are modeled in a neural language model (NLM), highlighting how linguistic information encoded in representations changes when the model learns to predict complexity.

Interpreting Neural Language Models for Linguistic Complexity Assessment

This thesis presents a model-driven study of multiple phenomena associated with linguistic complexity, and how those get encoded by neural language models' learned representations.

UmBERTo-MTSA@ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations

This work describes a self-supervised data augmentation approach used to improve learning models' performances when only a moderate amount of labeled data is available.

ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation

We present ETC-NLG, an approach leveraging topic modeling annotations to enable fully-unsupervised End-to-end Topic-Conditioned Natural Language Generation over emergent topics in unlabeled document collections.

ICLR 2020 Trends: Better & Faster Transformers for Natural Language Processing

A summary of promising directions from ICLR 2020 for better and faster pretrained tranformers language models.