A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification. (arXiv:2110.07792v2 [cs.CL] UPDATED)

We present a multilingual bag-of-entities model that effectively boosts the
performance of zero-shot cross-lingual text classification by extending a
multilingual pre-trained language model (e.g., M-BERT). It leverages the
multilingual nature of Wikidata: entities in multiple languages representing
the same concept are defined with a unique identifier. This enables entities
described in multiple languages to be represented using shared embeddings. A
model trained on entity features in a resource-rich language can thus be
directly applied to other languages. Our experimental results …

arxiv bag classification cross-lingual text text classification