Effectiveness of English Intermediate-Task Training Across Language Families in XTREME Benchmark

Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as most languages in the world are under-resourced. Here, we consider the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English. We show that this challenging setup can be approached using meta-learning, where, in addition to training a source language model, another model

Research goal: How does the effectiveness of English intermediate-task training vary across different language families in the XTREME benchmark when measured by accuracy gains in zero-shot cross-lingual transfer?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.