@inproceedings{jhalani-etal-2024-precision,
    title = "Precision Empowers, Excess Distracts: Visual Question Answering With Dynamically Infused Knowledge In Language Models",
    author = "Jhalani, Manas  and
      K M, Annervaz  and
      Bhattacharyya, Pushpak",
    editor = "Lalitha Devi, Sobha  and
      Arora, Karunesh",
    booktitle = "Proceedings of the 21st International Conference on Natural Language Processing (ICON)",
    month = dec,
    year = "2024",
    address = "AU-KBC Research Centre, Chennai, India",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.icon-1.3/",
    pages = "21--36",
    abstract = "In the realm of multimodal tasks, Visual Question Answering (VQA) plays a crucial role by addressing natural language questions grounded in visual content. Knowledge-Based Visual Question Answering (KBVQA) advances this concept by adding external knowledge along with images to respond to questions. We introduce an approach for KBVQA, augmenting the existing vision-language transformer encoder-decoder (OFA) model . Our main contribution involves enhancing questions by incorporating relevant external knowledge extracted from knowledge graphs, using a dynamic triple extraction"
}