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

This paper presents a quantitative fine-grained manual evaluation approach tocomparing the performance of different machine translation (MT) systems. Webuild upon the well-established Multidimensional Quality Metrics (MQM) errortaxonomy and implement a novel method that assesses whether the differences inperformance for MQM error types between different MT systems are statisticallysignificant. We conduct a case study for English-to-Croatian, a languagedirection that involves translating into a morphologically rich language, forwhich we compare three MT systems belonging to different paradigms: purephrase-based, factored phrase-based and neural. First, we design anMQM-compliant error taxonomy tailored to the relevant linguistic phenomena ofSlavic languages, which made the annotation process feasible and accurate.Errors in MT outputs were then annotated by two annotators following thistaxonomy. Subsequently, we carried out a statistical analysis which showed thatthe best-performing system (neural) reduces the errors produced by the worstsystem (pure phrase-based) by more than half (54\%). Moreover, we conducted anadditional analysis of agreement errors in which we distinguished between short(phrase-level) and long distance (sentence-level) errors. We discovered thatphrase-based MT approaches are of limited use for long distance agreementphenomena, for which neural MT was found to be especially effective.

Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian