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

Since their inception, embeddings have become a primary ingredient in manyflavours of Natural Language Processing (NLP) tasks supplanting earlier typesof representation. Even though multilingual embeddings have been used for theincreasing number of multilingual tasks, due to the scarcity of paralleltraining data, low-resource languages such as Sinhala, tend to focus more onmonolingual embeddings. Then when it comes to the aforementioned multi-lingualtasks, it is challenging to utilize these monolingual embeddings given thateven if the embedding spaces have a similar geometric arrangement due to anidentical training process, the embeddings of the languages considered are notaligned. This is solved by the embedding alignment task. Even in this,high-resource language pairs are in the limelight while low-resource languagessuch as Sinhala which is in dire need of help seem to have fallen by thewayside. In this paper, we try to align Sinhala and English word embeddingspaces based on available alignment techniques and introduce a benchmark forSinhala language embedding alignment. In addition to that, to facilitate thesupervised alignment, as an intermediate task, we also introduceSinhala-English alignment datasets. These datasets serve as our anchor datasetsfor supervised word embedding alignment. Even though we do not obtain resultscomparable to the high-resource languages such as French, German, or Chinese,we believe our work lays the groundwork for more specialized alignment betweenEnglish and Sinhala embeddings.

Sinhala-English Word Embedding Alignment: Introducing Datasets and Benchmark for a Low Resource Language