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

This paper presents the submissions by the University of Zurich to theSIGMORPHON 2017 shared task on morphological reinflection. The task is topredict the inflected form given a lemma and a set of morpho-syntacticfeatures. We focus on neural network approaches that can tackle the task in alimited-resource setting. As the transduction of the lemma into the inflectedform is dominated by copying over lemma characters, we propose two recurrentneural network architectures with hard monotonic attention that are strong atcopying and, yet, substantially different in how they achieve this. The firstapproach is an encoder-decoder model with a copy mechanism. The second approachis a neural state-transition system over a set of explicit edit actions,including a designated COPY action. We experiment with character alignment andfind that naive, greedy alignment consistently produces strong results for somelanguages. Our best system combination is the overall winner of the SIGMORPHON2017 Shared Task 1 without external resources. At a setting with 100 trainingsamples, both our approaches, as ensembles of models, outperform the next bestcompetitor.

Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection