PAELLA: Parameter-Efficient Lightweight Language-Agnostic Captioning Model
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 989 KB, PDF-dokument
We introduce PAELLA, a Parameter-Efficient Lightweight Language-Agnostic image captioning model designed to be both parameter and data-efficient using retrieval augmentation. The model is trained by learning a small mapping network with 34M parameters between a pre-trained visual model and a multilingual language model that is conditioned on two types of input: (i) the image itself, and (ii) a set of retrieved captions in the target language. The retrieved examples play a key role in guiding the model to generate captions across languages. Through retrieval, the model can be lightweight in terms of the number of trainable parameters, which only exist in its mapping network, and also in the amount of multilingual training data that is required. Experiments on the XM3600 dataset, featuring 36 languages, show that PAELLA can outperform or compete against some models with 3-77× more learned parameters and 35-863× more data, particularly in low-resource languages. We also find that PAELLA can be trained on only monolingual data and still show strong zero-shot abilities in other languages.
Originalsprog | Engelsk |
---|---|
Titel | Findings of the Association for Computational Linguistics : NAACL 2024 |
Redaktører | Kevin Duh, Helena Gomez, Steven Bethard |
Antal sider | 16 |
Forlag | Association for Computational Linguistics (ACL) |
Publikationsdato | 2024 |
Sider | 3549-3564 |
ISBN (Elektronisk) | 9798891761193 |
Status | Udgivet - 2024 |
Begivenhed | 2024 Findings of the Association for Computational Linguistics: NAACL 2024 - Mexico City, Mexico Varighed: 16 jun. 2024 → 21 jun. 2024 |
Konference
Konference | 2024 Findings of the Association for Computational Linguistics: NAACL 2024 |
---|---|
Land | Mexico |
By | Mexico City |
Periode | 16/06/2024 → 21/06/2024 |
Sponsor | Baidu, CapitalOne, et al., Grammarly, Megagon Labs, Otter.ai |
Bibliografisk note
Funding Information:
This research was supported by the Portuguese Recovery and Resilience Plan through project C645008882-00000055 (i.e., the Center For Responsible AI), and also by Funda\u00E7\u00E3o para a Ci\u00EAncia e Tecnologia (FCT), through the project with reference UIDB/50021/2020 (DOI:10.54499/UIDB/50021/2020) and the Ph.D. scholarship with reference 2020.06106.BD.
Publisher Copyright:
© 2024 Association for Computational Linguistics.
Links
- https://aclanthology.org/2024.findings-naacl.225/
Forlagets udgivne version
ID: 398633242