Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
This work addresses the problem of zero-shot and few-shot dependency parsing for multilingual NLP applications, representing an incremental advance in cross-lingual transfer techniques.
The paper tackles the challenge of aligning dynamic contextual embeddings across languages for multilingual transfer, achieving a 6.8-point average improvement in dependency parsing accuracy over previous state-of-the-art methods on six languages.
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.