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

Statistical language models conventionally implement representation learningbased on the contextual distribution of words or other formal units, whereasany information related to the logographic features of written text are oftenignored, assuming they should be retrieved relying on the cooccurencestatistics. On the other hand, as language models become larger and requiremore data to learn reliable representations, such assumptions may start to fallback, especially under conditions of data sparsity. Many languages, includingChinese and Vietnamese, use logographic writing systems where surface forms arerepresented as a visual organization of smaller graphemic units, which oftencontain many semantic cues. In this paper, we present a novel study whichexplores the benefits of providing language models with logographic informationin learning better semantic representations. We test our hypothesis in thenatural language inference (NLI) task by evaluating the benefit of computingmulti-modal representations that combine contextual information with glyphinformation. Our evaluation results in six languages with different typologyand writing systems suggest significant benefits of using multi-modalembeddings in languages with logograhic systems, especially for words with lessoccurence statistics.

Logographic Information Aids Learning Better Representations for Natural Language Inference