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

Word alignment is essential for the downstream cross-lingual languageunderstanding and generation tasks. Recently, the performance of the neuralword alignment models has exceeded that of statistical models. However, theyheavily rely on sophisticated translation models. In this study, we propose asuper lightweight unsupervised word alignment model named MirrorAlign, in whichbidirectional symmetric attention trained with a contrastive learning objectiveis introduced, and an agreement loss is employed to bind the attention maps,such that the alignments follow mirror-like symmetry hypothesis. Experimentalresults on several public benchmarks demonstrate that our model achievescompetitive, if not better, performance compared to the state of the art inword alignment while significantly reducing the training and decoding time onaverage. Further ablation analysis and case studies show the superiority of ourproposed MirrorAlign. Notably, we recognize our model as a pioneer attempt tounify bilingual word embedding and word alignments. Encouragingly, our approachachieves {16.4X speedup} against GIZA++, and {50X parameter compression}compared with the Transformer-based alignment methods. We release our code tofacilitate the community: https://github.com/moore3930/MirrorAlign.

MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning