Publications - sign-language-translation

Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language ModelsWorkshop paper

Pedro Dal Bianco, Jean Paul Nunes Reinhold, Oscar Stanchi, Facundo Quiroga, Franco Ronchetti, Ulisses Brisolara Corrêa

GenSign Workshop @ CVPR 2026

A large language model (GPT-4o) writes paraphrases of the target sentences to augment sign language translation data: pre-train on the augmented corpus, then fine-tune on the original references. Evaluated on PHOENIX14T, GSL and LSA-T, with lexical metrics and an LLM-as-a-Judge semantic evaluation.

sign-language-translation data-augmentation llm

Traducción automática de lengua de señas en español utilizando Deep LearningPhD thesis

Pedro Dal Bianco

PhD thesis, Facultad de Informática, Universidad Nacional de La Plata, 2026

PhD thesis (in Spanish) on translating Argentinian Sign Language into written Spanish with little data: the LSA-T corpus, a compact gloss-free pose-based Transformer, multilingual training and LLM paraphrases of the targets, and a study of what the model's attention learns.

sign-language-translation argentinian-sign-language multilingual interpretability

Multilingual Sign Language Translation with Unified Datasets and Pose-Based TransformersWorkshop paper

Pedro Dal Bianco, Oscar Stanchi, Facundo Quiroga, Franco Ronchetti

Workshop on Sign Language Processing (WSLP), IJCNLP-AACL 2025

One pose-based translation model trained jointly on German, Greek, Argentinian and Indian sign languages through a standardized data layer. Multilingual pre-training followed by a short language-specific fine-tuning beats the monolingual baselines on three of the four datasets.

sign-language-translation multilingual pose-based transformers

SignAttention: On the Interpretability of Transformer Models for Sign Language TranslationWorkshop paper

Pedro Dal Bianco*, Oscar Stanchi*, Facundo Quiroga, Franco Ronchetti, Enzo Ferrante

Interpretable AI Workshop (IAI) and LatinX in AI Workshop (oral), NeurIPS 2024

The first comprehensive interpretability analysis of a Transformer sign language translation model, on Greek Sign Language. The model attends to clusters of frames aligned diagonally with the glosses, and shifts from the video to its previous predictions as the translation progresses.

sign-language-translation interpretability transformers

A Study on pose-based deep learning models for gloss-free Sign Language TranslationJournal article

Pedro Dal Bianco, Gastón Ríos, Waldo Hasperué, Oscar Stanchi, Facundo Quiroga, Franco Ronchetti

Journal of Computer Science and Technology (JCS&T) 24(2), e09, 2024

A gloss-free, pose-based Transformer for sign language translation. Using pose keypoints instead of video greatly reduces the size of the data and of the model. Trained and evaluated on RWTH-Phoenix-2014T and the Greek Sign Language dataset (GSL).

sign-language-translation gloss-free pose-based transformers

LSA-T: The First Continuous Argentinian Sign Language Dataset for Sign Language TranslationConference paper

Pedro Dal Bianco, Gastón Ríos, Franco Ronchetti, Facundo Quiroga, Oscar Stanchi, Waldo Hasperué, Alejandro Rosete

IBERAMIA 2022, Ibero-American Conference on Artificial Intelligence (LNCS, Springer)

The first continuous Argentinian Sign Language (LSA) dataset: 14,880 sentence-level videos from the CN Sordos YouTube channel, with Spanish labels and keypoints for each signer, a method to infer the active signer, a visualization tool and a baseline translation model.

sign-language-translation dataset argentinian-sign-language