UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation

被引:0
|
作者
Ogezi, Michael [1 ]
Hauer, Bradley [1 ]
Omarov, Talgat [1 ]
Shi, Ning [1 ]
Kondrak, Grzegorz [1 ]
机构
[1] Univ Alberta, Dept Comp Sci, Alberta Machine Intelligence Inst, Edmonton, AB, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We describe the systems of the University of Alberta team for the SemEval-2023 Visual Word Sense Disambiguation (V-WSD) Task. We present a novel algorithm that leverages glosses retrieved from BabelNet, in combination with text and image encoders. Furthermore, we compare language-specific encoders against the application of English encoders to translated texts. As the contexts given in the task datasets are extremely short, we also experiment with augmenting these contexts with descriptions generated by a language model. This yields substantial improvements in accuracy. We describe and evaluate additional V-WSD methods which use image generation and text-conditioned image segmentation. Overall, the results of our official submission rank us 18 out of 56 teams. Some of our unofficial results are even better than the official ones. Our code is publicly available at https://github.com/UAlberta-NLP/v-wsd.
引用
收藏
页码:2043 / 2051
页数:9
相关论文
共 50 条
  • [31] lazybob at SemEval-2023 Task 9: Quantifying Intimacy of Multilingual Tweets with Multi-Task Learning
    Yuan, Mengfei
    Chen, Cheng
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 927 - 933
  • [32] HULAT at SemEval-2023 Task 9: Data Augmentation for Pre-trained Transformers Applied to Multilingual Tweet Intimacy Analysis
    Segura-Bedmar, Isabel
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 177 - 183
  • [33] iREL at SemEval-2023 Task 9: Improving understanding of multilingual Tweets using Translation-Based Augmentation and Domain Adapted Pre-Trained Models
    Singh, Bhavyajeet
    Maity, Ankita
    Kandru, Pavan
    Hari, Aditya
    Varma, Vasudeva
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 2052 - 2057
  • [34] NLPeople at SemEval-2023 Task 2: A Staged Approach for Multilingual Named Entity Recognition
    Elkaref, Mohab
    Herr, Nathan
    Tanaka, Shinnosuke
    De Mel, Geeth
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1148 - 1153
  • [35] RCLN at SemEval-2023 Task 1: Leveraging Stable Diffusion and Image Captions for Visual WSD
    Mijatovic, Antonina
    Borisova, Ekaterina
    Buscaldi, Davide
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 2174 - 2178
  • [36] OPI at SemEval-2023 Task 9: A Simple But Effective Approach to Multilingual Tweet Intimacy Analysis
    Dadas, Slawomir
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 150 - 154
  • [37] ACCEPT at SemEval-2023 Task 3: An Ensemble-based Approach to Multilingual Framing Detection
    Heinisch, Philipp
    Plenz, Moritz
    Frank, Anette
    Cimiano, Philipp
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1347 - 1358
  • [38] IXA/Cogcomp at SemEval-2023 Task 2: Context-enriched Multilingual Named Entity Recognition using Knowledge Bases
    Garcia-Ferrero, Iker
    Ander Campos, Jon
    Sainz, Oscar
    Salaberria, Ander
    Roth, Dan
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1335 - 1346
  • [39] ChaPat at SemEval-2023 Task 9: Text Intimacy Analysis using Ensembles of Multilingual Transformers
    Chavan, Tanmay
    Patwardhan, Ved
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 1304 - 1310
  • [40] University of Hildesheim at SemEval-2023 Task 1: Combining Pre-trained Multimodal and Generative Models for Image Disambiguation
    Diem, Sebastian
    Im, Chan Jong
    Mandl, Thomas
    17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023, 2023, : 130 - 135