In this cross-country research project, the MEMEM team will investigate how multilingual embeddings (MLE) respond to linguistic and cultural differences in contemporary AI and computational methods. MLE play a specific role in mapping equivalent contents across languages and contexts. Specifically, the researchers will use MLE to measure gendered biases and discrimination in Austrian and Israeli media discourses about political topics. Further investigations will then show how and when mappings deviate from valid equivalence, and what differences in the underlying data are responsible for these shifts. Finally, MEMEM aims to discuss implications for cross-lingual AI and textual research and propose a research agenda toward advancing the accuracy and accountability of cross-lingual computational text analysis.

The project Multilingual Embeddings as Maps of Equivalent Meaning (MEMEM) receives funding from the UNIVIE-HUJI Joint Research Grant program for a period of 18 months. The program aims to enhance and deepen the partnership between the University of Vienna and the Hebrew University of Jerusalem, Israel. Fabienne Lind will lead the project as principal investigator at our Department (further project members include Hajo Boomgaarden, Annie Waldherr, Jana Bernhard-Harrer, and Ahrabhi Kathirgamalingam), with Christian Baden directing the research at HUJI. In total, € 10.000 will be available for a variety of activities like traveling and the organization of events, among others.

Multilingual Embeddings as Maps of Equivalent Meaning (MEMEM)

Funding organization: University of Vienna | HUJI-UNIVIE Joint Research Grant
PI: Fabienne Lind • Christian Baden
Duration: 2024-2026
Funding: € 10.000