most citedCross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

11 citations · 11 across the 1 of their papers we have counts for

collaborators

2 papers

cs.CL2019

SenseBERT: Driving Some Sense into BERT

Yoav Levine, Barak Lenz, Or Dagan +6

The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision t…

cs.CL2019★ 11 cited

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

Tal Schuster, Ori Ram, Regina Barzilay +1

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown t…