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

Multi-criteria Chinese word segmentation (MCCWS) aims to exploit therelations among the multiple heterogeneous segmentation criteria and furtherimprove the performance of each single criterion. Previous work usually regardsMCCWS as different tasks, which are learned together under the multi-tasklearning framework. In this paper, we propose a concise but effective unifiedmodel for MCCWS, which is fully-shared for all the criteria. By leveraging thepowerful ability of the Transformer encoder, the proposed unified model cansegment Chinese text according to a unique criterion-token indicating theoutput criterion. Besides, the proposed unified model can segment bothsimplified and traditional Chinese and has an excellent transfer capability.Experiments on eight datasets with different criteria show that our modeloutperforms our single-criterion baseline model and other multi-criteriamodels. Source codes of this paper are available on Githubhttps://github.com/acphile/MCCWS.

A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder