Karen Hambardzumyan
K. Hambardzumyan, H. Khachatrian, and J. May
Abstract:
Contextualized word embeddings like BERT enabled signifi- cant advances in many natural language processing tasks. Recently, mul- tilingual versions of such embeddings were trained on large text corpora of more than 100 languages. In this paper we investigate how well such embeddings perform in zero-shot cross lingual transfer for an event ex- traction task. In particular, we analyze the impact of the alignment of contextualized word embeddings using a parallel corpus on the perfor- mance of the downstream task. |