Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.17918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929331467452416 |
|---|---|
| author | Mickus, Timothee Vázquez, Raúl Attieh, Joseph |
| author_facet | Mickus, Timothee Vázquez, Raúl Attieh, Joseph |
| contents | Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges, have been argued to improve the generalization capabilities of models by fostering language-independent representations. In the present paper, we study whether modularity affects translation quality; as well as how well modular architectures generalize across different evaluation scenarios. For a given computational budget, we find non-modular architectures to be always comparable or preferable to all modular designs we study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17918 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures Mickus, Timothee Vázquez, Raúl Attieh, Joseph Computation and Language Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges, have been argued to improve the generalization capabilities of models by fostering language-independent representations. In the present paper, we study whether modularity affects translation quality; as well as how well modular architectures generalize across different evaluation scenarios. For a given computational budget, we find non-modular architectures to be always comparable or preferable to all modular designs we study. |
| title | I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.17918 |