Zero-shot Cross-Linguistic Learning of Event Semantics
This addresses the challenge of event semantics prediction for low-resource languages, though it is incremental as it builds on existing cross-lingual methods.
The paper tackled the problem of predicting lexical aspects across typologically diverse languages without annotated data, achieving zero-shot cross-lingual learning by leveraging similarities in how speakers frame image content.
Typologically diverse languages offer systems of lexical and grammatical aspect that allow speakers to focus on facets of event structure in ways that comport with the specific communicative setting and discourse constraints they face. In this paper, we look specifically at captions of images across Arabic, Chinese, Farsi, German, Russian, and Turkish and describe a computational model for predicting lexical aspects. Despite the heterogeneity of these languages, and the salient invocation of distinctive linguistic resources across their caption corpora, speakers of these languages show surprising similarities in the ways they frame image content. We leverage this observation for zero-shot cross-lingual learning and show that lexical aspects can be predicted for a given language despite not having observed any annotated data for this language at all.