# Retrieval Augmented Cross-Modal Tag Recommendation in Software Q&A Sites

arXiv: https://arxiv.org/abs/2402.03635 · HTML: https://mlsanity.com/paper/2402.03635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 4 of 4)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues](https://mlsanity.com/paper/2203.06419/) (2022)
- [Cross-Modal Retrieval Augmentation for Multi-Modal Classification](https://mlsanity.com/paper/2104.08108/) (2021)

## Abstract (arXiv)

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.