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

Traditionally, many text-mining tasks treat individual word-tokens as thefinest meaningful semantic granularity. However, in many languages andspecialized corpora, words are composed by concatenating semanticallymeaningful subword structures. Word-level analysis cannot leverage the semanticinformation present in such subword structures. With regard to word embeddingtechniques, this leads to not only poor embeddings for infrequent words inlong-tailed text corpora but also weak capabilities for handlingout-of-vocabulary words. In this paper we propose MorphMine for unsupervisedmorpheme segmentation. MorphMine applies a parsimony criterion tohierarchically segment words into the fewest number of morphemes at each levelof the hierarchy. This leads to longer shared morphemes at each level ofsegmentation. Experiments show that MorphMine segments words in a variety oflanguages into human-verified morphemes. Additionally, we experimentallydemonstrate that utilizing MorphMine morphemes to enrich word embeddingsconsistently improves embedding quality on a variety of of embeddingevaluations and a downstream language modeling task.

Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings