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

NAACL 2019  Â·  Tal Schuster, Ori Ram, Regina Barzilay, Amir Globerson ·

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their static counterparts, aligning them poses a challenge due to their dynamic nature. To this end, we construct context-independent variants of the original monolingual spaces and utilize their mapping to derive an alignment for the context-dependent spaces. This mapping readily supports processing of a target language, improving transfer by context-aware embeddings. Our experimental results demonstrate the effectiveness of this approach for zero-shot and few-shot learning of dependency parsing. Specifically, our method consistently outperforms the previous state-of-the-art on 6 tested languages, yielding an improvement of 6.8 LAS points on average.

PDF Abstract NAACL 2019 PDF NAACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Cross-lingual zero-shot dependency parsing Universal Dependency Treebank Cross-Lingual ELMo LAS 77.3 # 1
UAS 84.2 # 1


No methods listed for this paper. Add relevant methods here