Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2402.03635 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917582961901568 |
|---|---|
| author | Lu, Sijin Xu, Pengyu Liu, Bing Sun, Hongjian Jing, Liping Yu, Jian |
| author_facet | Lu, Sijin Xu, Pengyu Liu, Bing Sun, Hongjian Jing, Liping Yu, Jian |
| contents | Posts in software Q\&A sites often consist of three main parts: title, description and code, which are interconnected and jointly describe the question. Existing tag recommendation methods often treat different modalities as a whole or inadequately consider the interaction between different modalities. Additionally, they focus on extracting information directly from the post itself, neglecting the information from external knowledge sources. Therefore, we propose a Retrieval Augmented Cross-Modal (RACM) Tag Recommendation Model in Software Q\&A Sites. Specifically, we first use the input post as a query and enhance the representation of different modalities by retrieving information from external knowledge sources. For the retrieval-augmented representations, we employ a cross-modal context-aware attention to leverage the main modality description for targeted feature extraction across the submodalities title and code. In the fusion process, a gate mechanism is employed to achieve fine-grained feature selection, controlling the amount of information extracted from the submodalities. Finally, the fused information is used for tag recommendation. Experimental results on three real-world datasets demonstrate that our model outperforms the state-of-the-art counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03635 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieval Augmented Cross-Modal Tag Recommendation in Software Q&A Sites Lu, Sijin Xu, Pengyu Liu, Bing Sun, Hongjian Jing, Liping Yu, Jian Information Retrieval Posts in software Q\&A sites often consist of three main parts: title, description and code, which are interconnected and jointly describe the question. Existing tag recommendation methods often treat different modalities as a whole or inadequately consider the interaction between different modalities. Additionally, they focus on extracting information directly from the post itself, neglecting the information from external knowledge sources. Therefore, we propose a Retrieval Augmented Cross-Modal (RACM) Tag Recommendation Model in Software Q\&A Sites. Specifically, we first use the input post as a query and enhance the representation of different modalities by retrieving information from external knowledge sources. For the retrieval-augmented representations, we employ a cross-modal context-aware attention to leverage the main modality description for targeted feature extraction across the submodalities title and code. In the fusion process, a gate mechanism is employed to achieve fine-grained feature selection, controlling the amount of information extracted from the submodalities. Finally, the fused information is used for tag recommendation. Experimental results on three real-world datasets demonstrate that our model outperforms the state-of-the-art counterparts. |
| title | Retrieval Augmented Cross-Modal Tag Recommendation in Software Q&A Sites |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2402.03635 |