@inproceedings{patil-etal-2023-rahul,
    title = "Rahul Patil at {S}em{E}val-2023 Task 1: {V}-{WSD}: Visual Word Sense Disambiguation",
    author = "Patil, Rahul  and
      Patel, Pinal  and
      Patel, Charin  and
      Verma, Mangal",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.semeval-1.176/",
    doi = "10.18653/v1/2023.semeval-1.176",
    pages = "1271--1275",
    abstract = "Semeval 2023 task 1: VWSD, In this paper, we propose an ensemble of two Neural network systems that ranks 10 images given a word and limited textual context. We have used openAI Clip based models for the English language and multilingual text-to-text translation models for Farsi-to-English and Italian-to-English. Additionally, we propose a system that learns from multilingual bert-base embeddings for text and resnet101 embeddings for the image. Considering all the three languages into account this system has achieved the fourth rank."
}