English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cross-lingual transfer is a leading technique for parsing low-resourcelanguages in the absence of explicit supervision. Simple `direct transfer' of alearned model based on a multilingual input encoding has provided a strongbenchmark. This paper presents a method for unsupervised cross-lingual transferthat improves over direct transfer systems by using their output as implicitsupervision as part of self-training on unlabelled text in the target language.The method assumes minimal resources and provides maximal flexibility by (a)accepting any pre-trained arc-factored dependency parser; (b) assuming noaccess to source language data; (c) supporting both projective andnon-projective parsing; and (d) supporting multi-source transfer. With Englishas the source language, we show significant improvements over state-of-the-arttransfer models on both distant and nearby languages, despite our conceptuallysimpler approach. We provide analyses of the choice of source languages formulti-source transfer, and the advantage of non-projective parsing. Our code isavailable online.

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation