Selected Publications | Gabriele Sarti

Selected Publications

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

We propose DecoderLens, a method to evaluate the iterative refinement of representations in encoder-decoder Transformer models.

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

We introduce PECoRe, an interpretability framework for identifying context dependence in language model generations.

RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

We introduce Retrieval and Attribute-Marking enhanced Prompting (RAMP) to perform attribute-controlled MT with multilingual LLMs.

Are Character-level Translations Worth the Wait? Comparing Character- and Subword-level Models for Machine Translation

We analyze input contributions of char-level MT models and show how they modulate word and character-level information.

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

DivEMT is a publicly available post-editing study of Neural Machine Translation over a typologically diverse set of target languages.

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

IT5s are the first encoder-decoder transformers pretrained on more than 40 billion Italian words.

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.

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 …

Teaching NLP with Bracelets and Restaurant Menus: An Interactive Workshop for Italian Students

We developed an interactive workshop designed to illustrate the NLP and computational linguistics to Italian high schoolers.

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 …

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 …

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 …

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 …