Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking
This addresses the problem of linking entities across languages for multilingual NLP applications, representing an incremental improvement with specific gains.
The paper tackled cross-language entity linking by proposing a neural ranking architecture using multilingual BERT, achieving robust performance in monolingual and multilingual settings, with surprisingly strong zero-shot transfer results.
Cross-language entity linking grounds mentions in multiple languages to a single-language knowledge base. We propose a neural ranking architecture for this task that uses multilingual BERT representations of the mention and the context in a neural network. We find that the multilingual ability of BERT leads to robust performance in monolingual and multilingual settings. Furthermore, we explore zero-shot language transfer and find surprisingly robust performance. We investigate the zero-shot degradation and find that it can be partially mitigated by a proposed auxiliary training objective, but that the remaining error can best be attributed to domain shift rather than language transfer.