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 the IMS contribution to the PolEval 2018 Shared Task. Wesubmitted systems for both of the Subtasks of Task 1. In Subtask (A), which wasabout dependency parsing, we used our ensemble system from the CoNLL 2017 UDShared Task. The system first preprocesses the sentences with a CRFPOS/morphological tagger and predicts supertags with a neural tagger. Then, itemploys multiple instances of three different parsers and merges their outputsby applying blending. The system achieved the second place out of fourparticipating teams. In this paper we show which components of the system werethe most responsible for its final performance.  The goal of Subtask (B) was to predict enhanced graphs. Our approachconsisted of two steps: parsing the sentences with our ensemble system fromSubtask (A), and applying 12 simple rules to obtain the final dependencygraphs. The rules introduce additional enhanced arcs only for tokens with"conj" heads (conjuncts). They do not predict semantic relations at all. Thesystem ranked first out of three participating teams. In this paper we showexamples of rules we designed and analyze the relation between the quality ofautomatically parsed trees and the accuracy of the enhanced graphs.

IMS at the PolEval 2018: A Bulky Ensemble Depedency Parser meets 12 Simple Rules for Predicting Enhanced Dependencies in Polish