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

Inferring implicit discourse relations in natural language text is the mostdifficult subtask in discourse parsing. Surface features achieve goodperformance, but they are not readily applicable to other languages withoutsemantic lexicons. Previous neural models require parses, surface features, ora small label set to work well. Here, we propose neural network models that arebased on feedforward and long-short term memory architecture without anysurface features. To our surprise, our best configured feedforward architectureoutperforms LSTM-based model in most cases despite thorough tuning. Undervarious fine-grained label sets and a cross-linguistic setting, our feedforwardmodels perform consistently better or at least just as well as systems thatrequire hand-crafted surface features. Our models present the first neuralChinese discourse parser in the style of Chinese Discourse Treebank, showingthat our results hold cross-linguistically.

Neural Network Models for Implicit Discourse Relation Classification in English and Chinese without Surface Features