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

For over thirty years, researchers have developed and analyzed methods forlatent tree induction as an approach for unsupervised syntactic parsing.Nonetheless, modern systems still do not perform well enough compared to theirsupervised counterparts to have any practical use as structural annotation oftext. In this work, we present a technique that uses distant supervision in theform of span constraints (i.e. phrase bracketing) to improve performance inunsupervised constituency parsing. Using a relatively small number of spanconstraints we can substantially improve the output from DIORA, an alreadycompetitive unsupervised parsing system. Compared with full parse treeannotation, span constraints can be acquired with minimal effort, such as witha lexicon derived from Wikipedia, to find exact text matches. Our experimentsshow span constraints based on entities improves constituency parsing onEnglish WSJ Penn Treebank by more than 5 F1. Furthermore, our method extends toany domain where span constraints are easily attainable, and as a case study wedemonstrate its effectiveness by parsing biomedical text from the CRAFTdataset.

Improved Latent Tree Induction with Distant Supervision via Span Constraints