Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning

Sheng Zhang, Miryam De Lhoneux, Anders Søgaard

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze, 2019), but only between related languages. However, source and training languages are rarely related, when parsing truly low-resource languages. To close this gap, we adopt a method from multi-task learning, which relies on automated curriculum learning, to dynamically optimize for parsing performance on outlier languages. We show that this approach is significantly better than uniform and size-proportional sampling in the zero-shot setting.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08555")
get_code_for_paper("2203.08555")
have("2203.08555")

Connect an agent — have() is free.