Text-to-Code Generation with Modality-relative Pre-training
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917586805981184 |
|---|---|
| author | Christopoulou, Fenia Zhang, Guchun Lampouras, Gerasimos |
| author_facet | Christopoulou, Fenia Zhang, Guchun Lampouras, Gerasimos |
| contents | Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain both natural and (linearised) programming language. Such approaches effectively map both modalities of the sequence into the same embedding space. However, programming language keywords (e.g. "while") often have very strictly defined semantics. As such, transfer learning from their natural language usage may not necessarily be beneficial to their code application and vise versa. Assuming an already pre-trained language model, in this work we investigate how sequence tokens can be adapted and represented differently, depending on which modality they belong to, and to the ultimate benefit of the downstream task. We experiment with separating embedding spaces between modalities during further model pre-training with modality-relative training objectives. We focus on text-to-code generation and observe consistent improvements across two backbone models and two test sets, measuring pass@$k$ and a novel incremental variation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05783 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text-to-Code Generation with Modality-relative Pre-training Christopoulou, Fenia Zhang, Guchun Lampouras, Gerasimos Computation and Language Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain both natural and (linearised) programming language. Such approaches effectively map both modalities of the sequence into the same embedding space. However, programming language keywords (e.g. "while") often have very strictly defined semantics. As such, transfer learning from their natural language usage may not necessarily be beneficial to their code application and vise versa. Assuming an already pre-trained language model, in this work we investigate how sequence tokens can be adapted and represented differently, depending on which modality they belong to, and to the ultimate benefit of the downstream task. We experiment with separating embedding spaces between modalities during further model pre-training with modality-relative training objectives. We focus on text-to-code generation and observe consistent improvements across two backbone models and two test sets, measuring pass@$k$ and a novel incremental variation. |
| title | Text-to-Code Generation with Modality-relative Pre-training |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.05783 |