Abstract
While there have been advances in Natural Language Processing (NLP), their success is mainly gained by applying a self-attention mechanism into single or multi-modalities. While this approach has brought significant improvements in multiple downstream tasks, it fails to capture the interaction between different entities. Therefore, we propose MM-GATBT, a multimodal graph representation learning model that captures not only the relational semantics within one modality but also the interactions between different modalities. Specifically, the proposed method constructs image-based node embedding which contains relational semantics of entities. Our empirical results show that MM-GATBT achieves state-of-the-art results among all published papers on the MM-IMDb dataset.- Anthology ID:
- 2022.naacl-srw.14
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
- Month:
- July
- Year:
- 2022
- Address:
- Hybrid: Seattle, Washington + Online
- Editors:
- Daphne Ippolito, Liunian Harold Li, Maria Leonor Pacheco, Danqi Chen, Nianwen Xue
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 106–112
- Language:
- URL:
- https://aclanthology.org/2022.naacl-srw.14
- DOI:
- 10.18653/v1/2022.naacl-srw.14
- Cite (ACL):
- Seung Byum Seo, Hyoungwook Nam, and Payam Delgosha. 2022. MM-GATBT: Enriching Multimodal Representation Using Graph Attention Network. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 106–112, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
- Cite (Informal):
- MM-GATBT: Enriching Multimodal Representation Using Graph Attention Network (Seo et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2022.naacl-srw.14.pdf
- Code
- sbseo/mm-gatbt