@inproceedings{bhattacharyya-etal-2025-one,
    title = "One More Modality: Does {A}bstract {M}eaning {R}epresentation Benefit Visual Question Answering?",
    author = "Bhattacharyya, Abhidip  and
      Markle, Emma  and
      Wein, Shira",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.82/",
    doi = "10.18653/v1/2025.findings-emnlp.82",
    pages = "1560--1572",
    ISBN = "979-8-89176-335-7",
    abstract = "Visual Question Answering (VQA) requires a vision-language model to reason over both visual and textual inputs to answer questions about images. In this work, we investigate whether incorporating explicit semantic information, in the form of Abstract Meaning Representation (AMR) graphs, can enhance model performance{---}particularly in low-resource settings where training data is limited. We augment two vision-language models, LXMERT and BLIP-2, with sentence- and document-level AMRs and evaluate their performance under both full and reduced training data conditions. Our findings show that in well-resourced settings, models (in particular the smaller LXMERT) are negatively impacted by incorporating AMR without specialized training. However, in low-resource settings, AMR proves beneficial: LXMERT achieves up to a 13.1{\%} relative gain using sentence-level AMRs. These results suggest that while addition of AMR can lower the performance in some settings, in a low-resource setting AMR can serve as a useful semantic prior, especially for lower-capacity models trained on limited data."
}