Nearest Neighbour Few-Shot Learning for Cross-lingual Classification

Saab Mansour, M Saiful, Batool Haider

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• amazon-research/nearest-neighbor-crosslingual-classification
• amazon-research/nearest-neighborcrosslingual-classification

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient annotated data. Traditional fine-tuning of pre-trained models using only a few target samples can cause over-fitting. This can be quite limiting as most languages in the world are under-resourced. In this work, we investigate cross-lingual adaptation using a simple nearest neighbor few-shot (< 15 samples) inference technique for classification tasks. We experiment using a total of 16 distinct languages across two NLP tasks-XNLI and PAWS-X. Our approach consistently improves traditional fine-tuning using only a handful of labeled samples in target locales. We also demonstrate its generalization capability across tasks. * Work done while Saiful was interning at Amazon AI 1 We loosely use the term LM to describe unsupervised pretrained models including Masked-LMs and Causal-LMs

For agents

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

get_harvested_code_for_paper("2109.02221")
get_code_for_paper("2109.02221")
have("2109.02221")

Connect an agent — have() is free.