Litcius/Paper detail

RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English

Stefan Grünewald, Annemarie Friedrich

202014 citationsDOIOpen Access PDF

Abstract

This paper presents our system at the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. Using a biaffine classifier architecture (Dozat and Manning, 2017) which operates directly on fine-tuned RoBERTa embeddings, our parser generates enhanced UD graphs by predicting the best dependency label (or absence of a dependency) for each pair of tokens in the sentence. We address label sparsity issues by replacing lexical items in relations with placeholders at prediction time, later retrieving them from the parse in a rule-based fashion. In addition, we ensure structural graph constraints using a simple set of heuristics. On the English blind test data, our system achieves a very high parsing accuracy, ranking 1 st out of 10 with an ELAS F1 score of 88.94 %.

Topics & Concepts

Computer scienceParsingHeuristicsDependency grammarNatural language processingArtificial intelligenceSentenceDependency (UML)Task (project management)Dependency graphGraphClassifier (UML)Theoretical computer scienceManagementEconomicsOperating systemNatural Language Processing TechniquesTopic ModelingText Readability and Simplification
RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English | Litcius