PAELLA: Parameter-Efficient Lightweight Language-Agnostic Captioning Model
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Fulltext
Final published version, 989 KB, PDF document
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.
Original language | English |
---|---|
Title of host publication | Findings of the Association for Computational Linguistics : NAACL 2024 |
Editors | Kevin Duh, Helena Gomez, Steven Bethard |
Number of pages | 16 |
Publisher | Association for Computational Linguistics (ACL) |
Publication date | 2024 |
Pages | 3549-3564 |
ISBN (Electronic) | 9798891761193 |
Publication status | Published - 2024 |
Event | 2024 Findings of the Association for Computational Linguistics: NAACL 2024 - Mexico City, Mexico Duration: 16 Jun 2024 → 21 Jun 2024 |
Conference
Conference | 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 |
Bibliographical note
Publisher Copyright:
© 2024 Association for Computational Linguistics.
Links
- https://aclanthology.org/2024.findings-naacl.225/
Final published version
ID: 398633242