Reconstructing Native Language Typology from Foreign Language Usage
This provides a method for linguists and psychologists to infer native language structures from foreign language usage, but it is incremental as it builds on existing cross-linguistic transfer research.
The paper tackled the problem of reconstructing native language typology from English as Second Language (ESL) texts by showing a strong correlation between structural features in ESL and native language typology, achieving 72.2% accuracy in unsupervised typology prediction.
Linguists and psychologists have long been studying cross-linguistic transfer, the influence of native language properties on linguistic performance in a foreign language. In this work we provide empirical evidence for this process in the form of a strong correlation between language similarities derived from structural features in English as Second Language (ESL) texts and equivalent similarities obtained from the typological features of the native languages. We leverage this finding to recover native language typological similarity structure directly from ESL text, and perform prediction of typological features in an unsupervised fashion with respect to the target languages. Our method achieves 72.2% accuracy on the typology prediction task, a result that is highly competitive with equivalent methods that rely on typological resources.