In this paper, we describe ParCorFull2. 0, a parallel corpus annotated with full coreference
chains for multiple languages, which is an extension of the existing corpus ParCorFull …

Context-aware neural machine translation (NMT) incorporates contextual information of
surrounding texts, that can improve the translation quality of document-level machine …

This thesis explores the variation in coreference patterns across language modes (ie,
spoken and written) and text genres. The significance of research on variation in language …

Translations help people understand content written in another language. However, even
correct literal translations do not fulfill that goal when people lack the necessary background …

The neural machine translation (NMT) has attracted great attention in recent years, as it has
yielded state-of-the-art translation quality. Despite of their promising results, many current …

A text is more than a sequence of sentences. To understand a text, one needs to recognize
how sentences are connected with each other and why they appear in a particular order. To …

Cohesion is crucial in writing and translation since it aids reader orientation. At the same
time, cohesion is highly language specific: Each language has its own grammatical and …