Research Area:  Machine Learning
Commonsense reasoning research has so far been limited to English. We aim to evaluate and improve popular multilingual language models (ML-LMs) to help advance commonsense reasoning (CSR) beyond English. We collect the Mickey Corpus, consisting of 561k sentences in 11 different languages, which can be used for analyzing and improving ML-LMs. We propose Mickey Probe, a language-agnostic probing task for fairly evaluating the common sense of popular ML-LMs across different languages. In addition, we also create two new datasets, X-CSQA and X-CODAH, by translating their English versions to 15 other languages, so that we can evaluate popular ML-LMs for cross-lingual commonsense reasoning. To improve the performance beyond English, we propose a simple yet effective method -- multilingual contrastive pre-training (MCP). It significantly enhances sentence representations, yielding a large performance gain on both benchmarks.
Keywords:  
Multilingual Language Models
Commonsense Reasoning
Multilingual Contrastive Pre-training
Computation and Language
Artificial Intelligence
Author(s) Name:  Bill Yuchen Lin, Seyeon Lee, Xiaoyang Qiao, Xiang Ren
Journal name:  Computation and Language
Conferrence name:  
Publisher name:  arXiv.2106.06937
DOI:  10.48550/arXiv.2106.06937
Volume Information:  
Paper Link:   https://arxiv.org/abs/2106.06937#