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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Sequence to sequence (seq2seq) models are often employed in settings wherethe target output is natural language. However, the syntactic properties of thelanguage generated from these models are not well understood. We explorewhether such output belongs to a formal and realistic grammar, by employing theEnglish Resource Grammar (ERG), a broad coverage, linguistically preciseHPSG-based grammar of English. From a French to English parallel corpus, weanalyze the parseability and grammatical constructions occurring in output froma seq2seq translation model. Over 93\% of the model translations are parseable,suggesting that it learns to generate conforming to a grammar. The model hastrouble learning the distribution of rarer syntactic rules, and we pinpointseveral constructions that differentiate translations between the referencesand our model.

Evaluating Syntactic Properties of Seq2seq Output with a Broad Coverage HPSG: A Case Study on Machine Translation