Papers by Mauro Cettolo
A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that multilingual NMT models can handle more than one translation direction with a single system. |
| Approach: | They propose a multilingual neural machine translation model that can handle more than one translation direction with a single system. |
| Outcome: | The proposed model performs well in low-resource settings against bilingual systems. |
Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? (2021.acl-long)
Copied to clipboard
Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, Marco Turchi
| Challenge: | a gap between direct approaches to speech translation (ST) and traditional cascade solutions has gradually decreased . a recent study found that the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other. |
| Approach: | They compare state-of-the-art systems representative of the two paradigms . they find subtle differences observed in their behavior are not sufficient . |
| Outcome: | The proposed system is compared with state-of-the-art systems representative of the two paradigms. |
Direct Speech Translation for Automatic Subtitling (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing models for automatic subtitling generate subtitles in the target language along with their timestamps. |
| Approach: | They propose a direct speech translation model that generates subtitles in the target language along with their timestamps with a single model. |
| Outcome: | The proposed model outperforms a cascade system on 7 language pairs and on new benchmarks. |
Evaluating Subtitle Segmentation for End-to-end Generation Systems (2022.lrec-1)
Copied to clipboard
| Challenge: | Subtitle segmentation can be evaluated with sequence segmentation metrics against a human reference, but cannot be applied when systems generate outputs different than the reference, e.g. with end-to-end subtitling systems. |
| Approach: | They propose to use Sigma to evaluate subtitle segmentation against a human reference and a boundary projection method to disentangle the effect of good segmentation from text quality. |
| Outcome: | The proposed method disentangles the effect of good segmentation from text quality and is compared with existing metrics. |
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling (2024.acl-long)
Copied to clipboard
| Challenge: | Subtitling is a crucial task for enhancing the accessibility of audiovisual content and relying on automatic transcripts for the three subtasks is uncharted territory. |
| Approach: | They propose a model capable of producing automatic subtitles, completely eliminating any dependence on intermediate transcripts also for timestamp prediction. |
| Outcome: | Experimental results show that the proposed model eliminates the need for intermediate transcripts for timestamp prediction across multiple language pairs and diverse conditions. |
Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing solutions to control speaker-related gender inflections in ST involve dedicated model retraining on gender-labeled data. |
| Approach: | They propose to use a gender-based inference-time solution to control speaker-related gender inflections in ST by replacing the implicitly learned internal language model with gender-specific external LMs. |
| Outcome: | The proposed approach outperforms the base models and the best training-time mitigation strategy by up to 31.0 and 1.6 points in gender accuracy, respectively, for feminine forms. |
Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing metrics for automatic subtitling are not yet fully explored. |
| Approach: | They propose to use machine translation metrics to measure post-editing effort in automatic subtitling to collect data on product-, process- and participant-based data. |
| Outcome: | The proposed metrics correlate with measures of post-editing effort in automatic subtitling. |
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages (2024.emnlp-main)
Copied to clipboard
Marco Gaido, Sara Papi, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
| Challenge: | Existing speech FMs fall short of full compliance with open-source principles . existing models do not have model weights, code, and training data publicly available . |
| Approach: | They propose to use a CC-BY license to create open-source speech FMs for EU languages . they collect suitable training data by surveying automatic speech recognition datasets . |
| Outcome: | The proposed model can be used in the 24 official languages of the European Union. |
CTC-based Compression for Direct Speech Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing studies have shown that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). |
| Approach: | They propose a method which performs a phone-informed compression of the input audio in direct ST models by exploiting the Connectionist Temporal Classification (CTC) they demonstrate that their method brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German) |
| Outcome: | The proposed method brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German) it reduces memory footprint by more than 10%, and is faster than previous approaches. |