Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2305.11074 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929296763781120 |
|---|---|
| author | Ye, Tong Wu, Lingfei Ma, Tengfei Zhang, Xuhong Du, Yangkai Liu, Peiyu Ji, Shouling Wang, Wenhai |
| author_facet | Ye, Tong Wu, Lingfei Ma, Tengfei Zhang, Xuhong Du, Yangkai Liu, Peiyu Ji, Shouling Wang, Wenhai |
| contents | Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their inability to access external knowledge. To address this limitation, an emerging trend is combining neural models with external knowledge through retrieval methods. Previous methods have relied on the sentence-level retrieval paradigm on the encoder side. However, this paradigm is coarse-grained, noise-filled and cannot directly take advantage of the high-quality retrieved summary tokens on the decoder side. In this paper, we propose a fine-grained Token-level retrieval-augmented mechanism (Tram) on the decoder side rather than the encoder side to enhance the performance of neural models and produce more low-frequency tokens in generating summaries. Furthermore, to overcome the challenge of token-level retrieval in capturing contextual code semantics, we also propose integrating code semantics into individual summary tokens. The results of extensive experiments and human evaluation show that our token-level retrieval-augmented approach significantly improves performance and is more interpretable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_11074 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization Ye, Tong Wu, Lingfei Ma, Tengfei Zhang, Xuhong Du, Yangkai Liu, Peiyu Ji, Shouling Wang, Wenhai Artificial Intelligence Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their inability to access external knowledge. To address this limitation, an emerging trend is combining neural models with external knowledge through retrieval methods. Previous methods have relied on the sentence-level retrieval paradigm on the encoder side. However, this paradigm is coarse-grained, noise-filled and cannot directly take advantage of the high-quality retrieved summary tokens on the decoder side. In this paper, we propose a fine-grained Token-level retrieval-augmented mechanism (Tram) on the decoder side rather than the encoder side to enhance the performance of neural models and produce more low-frequency tokens in generating summaries. Furthermore, to overcome the challenge of token-level retrieval in capturing contextual code semantics, we also propose integrating code semantics into individual summary tokens. The results of extensive experiments and human evaluation show that our token-level retrieval-augmented approach significantly improves performance and is more interpretable. |
| title | Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2305.11074 |